Epoch 1
Browse filesThis view is limited to 50 files because it contains too many changes.  
							See raw diff
- checkpoint-10000/optimizer.bin +3 -0
- checkpoint-10000/random_states_0.pkl +3 -0
- checkpoint-10000/scaler.pt +3 -0
- checkpoint-10000/scheduler.bin +3 -0
- checkpoint-10000/unet/config.json +60 -0
- checkpoint-10000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-10000/unet_ema/config.json +67 -0
- checkpoint-10000/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-10500/optimizer.bin +3 -0
- checkpoint-10500/random_states_0.pkl +3 -0
- checkpoint-10500/scaler.pt +3 -0
- checkpoint-10500/scheduler.bin +3 -0
- checkpoint-10500/unet/config.json +60 -0
- checkpoint-10500/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-10500/unet_ema/config.json +67 -0
- checkpoint-10500/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-11000/optimizer.bin +3 -0
- checkpoint-11000/random_states_0.pkl +3 -0
- checkpoint-11000/scaler.pt +3 -0
- checkpoint-11000/scheduler.bin +3 -0
- checkpoint-11000/unet/config.json +60 -0
- checkpoint-11000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-11000/unet_ema/config.json +67 -0
- checkpoint-11000/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-11500/optimizer.bin +3 -0
- checkpoint-11500/random_states_0.pkl +3 -0
- checkpoint-11500/scaler.pt +3 -0
- checkpoint-11500/scheduler.bin +3 -0
- checkpoint-11500/unet/config.json +60 -0
- checkpoint-11500/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-11500/unet_ema/config.json +67 -0
- checkpoint-11500/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-12000/optimizer.bin +3 -0
- checkpoint-12000/random_states_0.pkl +3 -0
- checkpoint-12000/scaler.pt +3 -0
- checkpoint-12000/scheduler.bin +3 -0
- checkpoint-12000/unet/config.json +60 -0
- checkpoint-12000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-12000/unet_ema/config.json +67 -0
- checkpoint-12000/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-12500/optimizer.bin +3 -0
- checkpoint-12500/random_states_0.pkl +3 -0
- checkpoint-12500/scaler.pt +3 -0
- checkpoint-12500/scheduler.bin +3 -0
- checkpoint-12500/unet/config.json +60 -0
- checkpoint-12500/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-12500/unet_ema/config.json +67 -0
- checkpoint-12500/unet_ema/diffusion_pytorch_model.bin +3 -0
- checkpoint-13000/optimizer.bin +3 -0
- checkpoint-13000/random_states_0.pkl +3 -0
    	
        checkpoint-10000/optimizer.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:5b090d607af6016381dfcf39870c8e914ab0c521cc23f63856141be27abe1a27
         | 
| 3 | 
            +
            size 126008021
         | 
    	
        checkpoint-10000/random_states_0.pkl
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:dd9d5b306c500cf427061ff05d876b3f966c3ff7c0296cf75f11614c19697acd
         | 
| 3 | 
            +
            size 14727
         | 
    	
        checkpoint-10000/scaler.pt
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:a5861e9596f8f8ce01b577bd4dd492e27f1e29316ddca8a2e44df0d7f6501728
         | 
| 3 | 
            +
            size 557
         | 
    	
        checkpoint-10000/scheduler.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:716a4c1cb77e6c92b6c8d28de079a6d120ebdd3b04b64c98719aa262ed9d67fa
         | 
| 3 | 
            +
            size 563
         | 
    	
        checkpoint-10000/unet/config.json
    ADDED
    
    | @@ -0,0 +1,60 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_class_name": "UNet2DConditionModel",
         | 
| 3 | 
            +
              "_diffusers_version": "0.16.1",
         | 
| 4 | 
            +
              "act_fn": "silu",
         | 
| 5 | 
            +
              "addition_embed_type": null,
         | 
| 6 | 
            +
              "addition_embed_type_num_heads": 64,
         | 
| 7 | 
            +
              "attention_head_dim": 8,
         | 
| 8 | 
            +
              "block_out_channels": [
         | 
| 9 | 
            +
                128,
         | 
| 10 | 
            +
                128,
         | 
| 11 | 
            +
                128,
         | 
| 12 | 
            +
                128
         | 
| 13 | 
            +
              ],
         | 
| 14 | 
            +
              "center_input_sample": false,
         | 
| 15 | 
            +
              "class_embed_type": null,
         | 
| 16 | 
            +
              "class_embeddings_concat": false,
         | 
| 17 | 
            +
              "conv_in_kernel": 3,
         | 
| 18 | 
            +
              "conv_out_kernel": 3,
         | 
| 19 | 
            +
              "cross_attention_dim": 256,
         | 
| 20 | 
            +
              "cross_attention_norm": null,
         | 
| 21 | 
            +
              "down_block_types": [
         | 
| 22 | 
            +
                "DownBlock2D",
         | 
| 23 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 24 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 25 | 
            +
                "DownBlock2D"
         | 
| 26 | 
            +
              ],
         | 
| 27 | 
            +
              "downsample_padding": 1,
         | 
| 28 | 
            +
              "dual_cross_attention": false,
         | 
| 29 | 
            +
              "encoder_hid_dim": null,
         | 
| 30 | 
            +
              "flip_sin_to_cos": true,
         | 
| 31 | 
            +
              "freq_shift": 0,
         | 
| 32 | 
            +
              "in_channels": 3,
         | 
| 33 | 
            +
              "layers_per_block": 2,
         | 
| 34 | 
            +
              "mid_block_only_cross_attention": null,
         | 
| 35 | 
            +
              "mid_block_scale_factor": 1,
         | 
| 36 | 
            +
              "mid_block_type": "UNetMidBlock2DCrossAttn",
         | 
| 37 | 
            +
              "norm_eps": 1e-05,
         | 
| 38 | 
            +
              "norm_num_groups": 32,
         | 
| 39 | 
            +
              "num_class_embeds": null,
         | 
| 40 | 
            +
              "only_cross_attention": false,
         | 
| 41 | 
            +
              "out_channels": 3,
         | 
| 42 | 
            +
              "projection_class_embeddings_input_dim": null,
         | 
| 43 | 
            +
              "resnet_out_scale_factor": 1.0,
         | 
| 44 | 
            +
              "resnet_skip_time_act": false,
         | 
| 45 | 
            +
              "resnet_time_scale_shift": "default",
         | 
| 46 | 
            +
              "sample_size": 256,
         | 
| 47 | 
            +
              "time_cond_proj_dim": null,
         | 
| 48 | 
            +
              "time_embedding_act_fn": null,
         | 
| 49 | 
            +
              "time_embedding_dim": null,
         | 
| 50 | 
            +
              "time_embedding_type": "positional",
         | 
| 51 | 
            +
              "timestep_post_act": null,
         | 
| 52 | 
            +
              "up_block_types": [
         | 
| 53 | 
            +
                "UpBlock2D",
         | 
| 54 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 55 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 56 | 
            +
                "UpBlock2D"
         | 
| 57 | 
            +
              ],
         | 
| 58 | 
            +
              "upcast_attention": false,
         | 
| 59 | 
            +
              "use_linear_projection": false
         | 
| 60 | 
            +
            }
         | 
    	
        checkpoint-10000/unet/diffusion_pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:0101a22b3345e80c6388de82e529415fb13b3dea20ef87ee2d119b4f2a338351
         | 
| 3 | 
            +
            size 63003985
         | 
    	
        checkpoint-10000/unet_ema/config.json
    ADDED
    
    | @@ -0,0 +1,67 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_class_name": "UNet2DConditionModel",
         | 
| 3 | 
            +
              "_diffusers_version": "0.16.1",
         | 
| 4 | 
            +
              "act_fn": "silu",
         | 
| 5 | 
            +
              "addition_embed_type": null,
         | 
| 6 | 
            +
              "addition_embed_type_num_heads": 64,
         | 
| 7 | 
            +
              "attention_head_dim": 8,
         | 
| 8 | 
            +
              "block_out_channels": [
         | 
| 9 | 
            +
                128,
         | 
| 10 | 
            +
                128,
         | 
| 11 | 
            +
                128,
         | 
| 12 | 
            +
                128
         | 
| 13 | 
            +
              ],
         | 
| 14 | 
            +
              "center_input_sample": false,
         | 
| 15 | 
            +
              "class_embed_type": null,
         | 
| 16 | 
            +
              "class_embeddings_concat": false,
         | 
| 17 | 
            +
              "conv_in_kernel": 3,
         | 
| 18 | 
            +
              "conv_out_kernel": 3,
         | 
| 19 | 
            +
              "cross_attention_dim": 256,
         | 
| 20 | 
            +
              "cross_attention_norm": null,
         | 
| 21 | 
            +
              "decay": 0.9999,
         | 
| 22 | 
            +
              "down_block_types": [
         | 
| 23 | 
            +
                "DownBlock2D",
         | 
| 24 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 25 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 26 | 
            +
                "DownBlock2D"
         | 
| 27 | 
            +
              ],
         | 
| 28 | 
            +
              "downsample_padding": 1,
         | 
| 29 | 
            +
              "dual_cross_attention": false,
         | 
| 30 | 
            +
              "encoder_hid_dim": null,
         | 
| 31 | 
            +
              "flip_sin_to_cos": true,
         | 
| 32 | 
            +
              "freq_shift": 0,
         | 
| 33 | 
            +
              "in_channels": 3,
         | 
| 34 | 
            +
              "inv_gamma": 1.0,
         | 
| 35 | 
            +
              "layers_per_block": 2,
         | 
| 36 | 
            +
              "mid_block_only_cross_attention": null,
         | 
| 37 | 
            +
              "mid_block_scale_factor": 1,
         | 
| 38 | 
            +
              "mid_block_type": "UNetMidBlock2DCrossAttn",
         | 
| 39 | 
            +
              "min_decay": 0.0,
         | 
| 40 | 
            +
              "norm_eps": 1e-05,
         | 
| 41 | 
            +
              "norm_num_groups": 32,
         | 
| 42 | 
            +
              "num_class_embeds": null,
         | 
| 43 | 
            +
              "only_cross_attention": false,
         | 
| 44 | 
            +
              "optimization_step": 10000,
         | 
| 45 | 
            +
              "out_channels": 3,
         | 
| 46 | 
            +
              "power": 0.75,
         | 
| 47 | 
            +
              "projection_class_embeddings_input_dim": null,
         | 
| 48 | 
            +
              "resnet_out_scale_factor": 1.0,
         | 
| 49 | 
            +
              "resnet_skip_time_act": false,
         | 
| 50 | 
            +
              "resnet_time_scale_shift": "default",
         | 
| 51 | 
            +
              "sample_size": 256,
         | 
| 52 | 
            +
              "time_cond_proj_dim": null,
         | 
| 53 | 
            +
              "time_embedding_act_fn": null,
         | 
| 54 | 
            +
              "time_embedding_dim": null,
         | 
| 55 | 
            +
              "time_embedding_type": "positional",
         | 
| 56 | 
            +
              "timestep_post_act": null,
         | 
| 57 | 
            +
              "up_block_types": [
         | 
| 58 | 
            +
                "UpBlock2D",
         | 
| 59 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 60 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 61 | 
            +
                "UpBlock2D"
         | 
| 62 | 
            +
              ],
         | 
| 63 | 
            +
              "upcast_attention": false,
         | 
| 64 | 
            +
              "update_after_step": 0,
         | 
| 65 | 
            +
              "use_ema_warmup": true,
         | 
| 66 | 
            +
              "use_linear_projection": false
         | 
| 67 | 
            +
            }
         | 
    	
        checkpoint-10000/unet_ema/diffusion_pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:bc0ddb8ade30df6a744e78e624e80ea61a1d347ff3fa9f5885eb12f029a23342
         | 
| 3 | 
            +
            size 62996305
         | 
    	
        checkpoint-10500/optimizer.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:b36d5996c5df654edb110905edc9bae08e11d110b43cf84c5b3b70f15de81f04
         | 
| 3 | 
            +
            size 126008021
         | 
    	
        checkpoint-10500/random_states_0.pkl
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:ea186ed1953c1461dfdb4b4f8cd64b90bf2f20d5c4795397be4eab2a032dedc9
         | 
| 3 | 
            +
            size 14727
         | 
    	
        checkpoint-10500/scaler.pt
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:df7dc3303bdc1a2737159ab5ce6ac6dfaf84d16b8f82e60421bc66305d6aac5e
         | 
| 3 | 
            +
            size 557
         | 
    	
        checkpoint-10500/scheduler.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:e010ff830775f5fe481ffd405dca09282028c243d72f575341640b2632c429b9
         | 
| 3 | 
            +
            size 563
         | 
    	
        checkpoint-10500/unet/config.json
    ADDED
    
    | @@ -0,0 +1,60 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_class_name": "UNet2DConditionModel",
         | 
| 3 | 
            +
              "_diffusers_version": "0.16.1",
         | 
| 4 | 
            +
              "act_fn": "silu",
         | 
| 5 | 
            +
              "addition_embed_type": null,
         | 
| 6 | 
            +
              "addition_embed_type_num_heads": 64,
         | 
| 7 | 
            +
              "attention_head_dim": 8,
         | 
| 8 | 
            +
              "block_out_channels": [
         | 
| 9 | 
            +
                128,
         | 
| 10 | 
            +
                128,
         | 
| 11 | 
            +
                128,
         | 
| 12 | 
            +
                128
         | 
| 13 | 
            +
              ],
         | 
| 14 | 
            +
              "center_input_sample": false,
         | 
| 15 | 
            +
              "class_embed_type": null,
         | 
| 16 | 
            +
              "class_embeddings_concat": false,
         | 
| 17 | 
            +
              "conv_in_kernel": 3,
         | 
| 18 | 
            +
              "conv_out_kernel": 3,
         | 
| 19 | 
            +
              "cross_attention_dim": 256,
         | 
| 20 | 
            +
              "cross_attention_norm": null,
         | 
| 21 | 
            +
              "down_block_types": [
         | 
| 22 | 
            +
                "DownBlock2D",
         | 
| 23 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 24 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 25 | 
            +
                "DownBlock2D"
         | 
| 26 | 
            +
              ],
         | 
| 27 | 
            +
              "downsample_padding": 1,
         | 
| 28 | 
            +
              "dual_cross_attention": false,
         | 
| 29 | 
            +
              "encoder_hid_dim": null,
         | 
| 30 | 
            +
              "flip_sin_to_cos": true,
         | 
| 31 | 
            +
              "freq_shift": 0,
         | 
| 32 | 
            +
              "in_channels": 3,
         | 
| 33 | 
            +
              "layers_per_block": 2,
         | 
| 34 | 
            +
              "mid_block_only_cross_attention": null,
         | 
| 35 | 
            +
              "mid_block_scale_factor": 1,
         | 
| 36 | 
            +
              "mid_block_type": "UNetMidBlock2DCrossAttn",
         | 
| 37 | 
            +
              "norm_eps": 1e-05,
         | 
| 38 | 
            +
              "norm_num_groups": 32,
         | 
| 39 | 
            +
              "num_class_embeds": null,
         | 
| 40 | 
            +
              "only_cross_attention": false,
         | 
| 41 | 
            +
              "out_channels": 3,
         | 
| 42 | 
            +
              "projection_class_embeddings_input_dim": null,
         | 
| 43 | 
            +
              "resnet_out_scale_factor": 1.0,
         | 
| 44 | 
            +
              "resnet_skip_time_act": false,
         | 
| 45 | 
            +
              "resnet_time_scale_shift": "default",
         | 
| 46 | 
            +
              "sample_size": 256,
         | 
| 47 | 
            +
              "time_cond_proj_dim": null,
         | 
| 48 | 
            +
              "time_embedding_act_fn": null,
         | 
| 49 | 
            +
              "time_embedding_dim": null,
         | 
| 50 | 
            +
              "time_embedding_type": "positional",
         | 
| 51 | 
            +
              "timestep_post_act": null,
         | 
| 52 | 
            +
              "up_block_types": [
         | 
| 53 | 
            +
                "UpBlock2D",
         | 
| 54 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 55 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 56 | 
            +
                "UpBlock2D"
         | 
| 57 | 
            +
              ],
         | 
| 58 | 
            +
              "upcast_attention": false,
         | 
| 59 | 
            +
              "use_linear_projection": false
         | 
| 60 | 
            +
            }
         | 
    	
        checkpoint-10500/unet/diffusion_pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:aebe2767eddec5964362bccb08e43d52c06578dd80580e530baf667c100d5287
         | 
| 3 | 
            +
            size 63003985
         | 
    	
        checkpoint-10500/unet_ema/config.json
    ADDED
    
    | @@ -0,0 +1,67 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_class_name": "UNet2DConditionModel",
         | 
| 3 | 
            +
              "_diffusers_version": "0.16.1",
         | 
| 4 | 
            +
              "act_fn": "silu",
         | 
| 5 | 
            +
              "addition_embed_type": null,
         | 
| 6 | 
            +
              "addition_embed_type_num_heads": 64,
         | 
| 7 | 
            +
              "attention_head_dim": 8,
         | 
| 8 | 
            +
              "block_out_channels": [
         | 
| 9 | 
            +
                128,
         | 
| 10 | 
            +
                128,
         | 
| 11 | 
            +
                128,
         | 
| 12 | 
            +
                128
         | 
| 13 | 
            +
              ],
         | 
| 14 | 
            +
              "center_input_sample": false,
         | 
| 15 | 
            +
              "class_embed_type": null,
         | 
| 16 | 
            +
              "class_embeddings_concat": false,
         | 
| 17 | 
            +
              "conv_in_kernel": 3,
         | 
| 18 | 
            +
              "conv_out_kernel": 3,
         | 
| 19 | 
            +
              "cross_attention_dim": 256,
         | 
| 20 | 
            +
              "cross_attention_norm": null,
         | 
| 21 | 
            +
              "decay": 0.9999,
         | 
| 22 | 
            +
              "down_block_types": [
         | 
| 23 | 
            +
                "DownBlock2D",
         | 
| 24 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 25 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 26 | 
            +
                "DownBlock2D"
         | 
| 27 | 
            +
              ],
         | 
| 28 | 
            +
              "downsample_padding": 1,
         | 
| 29 | 
            +
              "dual_cross_attention": false,
         | 
| 30 | 
            +
              "encoder_hid_dim": null,
         | 
| 31 | 
            +
              "flip_sin_to_cos": true,
         | 
| 32 | 
            +
              "freq_shift": 0,
         | 
| 33 | 
            +
              "in_channels": 3,
         | 
| 34 | 
            +
              "inv_gamma": 1.0,
         | 
| 35 | 
            +
              "layers_per_block": 2,
         | 
| 36 | 
            +
              "mid_block_only_cross_attention": null,
         | 
| 37 | 
            +
              "mid_block_scale_factor": 1,
         | 
| 38 | 
            +
              "mid_block_type": "UNetMidBlock2DCrossAttn",
         | 
| 39 | 
            +
              "min_decay": 0.0,
         | 
| 40 | 
            +
              "norm_eps": 1e-05,
         | 
| 41 | 
            +
              "norm_num_groups": 32,
         | 
| 42 | 
            +
              "num_class_embeds": null,
         | 
| 43 | 
            +
              "only_cross_attention": false,
         | 
| 44 | 
            +
              "optimization_step": 10500,
         | 
| 45 | 
            +
              "out_channels": 3,
         | 
| 46 | 
            +
              "power": 0.75,
         | 
| 47 | 
            +
              "projection_class_embeddings_input_dim": null,
         | 
| 48 | 
            +
              "resnet_out_scale_factor": 1.0,
         | 
| 49 | 
            +
              "resnet_skip_time_act": false,
         | 
| 50 | 
            +
              "resnet_time_scale_shift": "default",
         | 
| 51 | 
            +
              "sample_size": 256,
         | 
| 52 | 
            +
              "time_cond_proj_dim": null,
         | 
| 53 | 
            +
              "time_embedding_act_fn": null,
         | 
| 54 | 
            +
              "time_embedding_dim": null,
         | 
| 55 | 
            +
              "time_embedding_type": "positional",
         | 
| 56 | 
            +
              "timestep_post_act": null,
         | 
| 57 | 
            +
              "up_block_types": [
         | 
| 58 | 
            +
                "UpBlock2D",
         | 
| 59 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 60 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 61 | 
            +
                "UpBlock2D"
         | 
| 62 | 
            +
              ],
         | 
| 63 | 
            +
              "upcast_attention": false,
         | 
| 64 | 
            +
              "update_after_step": 0,
         | 
| 65 | 
            +
              "use_ema_warmup": true,
         | 
| 66 | 
            +
              "use_linear_projection": false
         | 
| 67 | 
            +
            }
         | 
    	
        checkpoint-10500/unet_ema/diffusion_pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:9a9ffebdad5f8dddae2f5153346c98ff7a75dd2b4116675eef75c9d7579992e0
         | 
| 3 | 
            +
            size 62996305
         | 
    	
        checkpoint-11000/optimizer.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:9f99a18b8660eabc917419721f0447562535c746d575566a242639883e7f661c
         | 
| 3 | 
            +
            size 126008021
         | 
    	
        checkpoint-11000/random_states_0.pkl
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:8c5f940a906ca49f86eed5a962a6426c1886f5e7960c0d62c6916a9899e36816
         | 
| 3 | 
            +
            size 14727
         | 
    	
        checkpoint-11000/scaler.pt
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:7fa181fa360d46feed4180ea17c8b6a4a879a9b4231c2e91aff2be20be9076cc
         | 
| 3 | 
            +
            size 557
         | 
    	
        checkpoint-11000/scheduler.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:4c94ae12037561999a6d2a3dcc05fdbbe7cd62e455f948746fc011252f09b7ea
         | 
| 3 | 
            +
            size 563
         | 
    	
        checkpoint-11000/unet/config.json
    ADDED
    
    | @@ -0,0 +1,60 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_class_name": "UNet2DConditionModel",
         | 
| 3 | 
            +
              "_diffusers_version": "0.16.1",
         | 
| 4 | 
            +
              "act_fn": "silu",
         | 
| 5 | 
            +
              "addition_embed_type": null,
         | 
| 6 | 
            +
              "addition_embed_type_num_heads": 64,
         | 
| 7 | 
            +
              "attention_head_dim": 8,
         | 
| 8 | 
            +
              "block_out_channels": [
         | 
| 9 | 
            +
                128,
         | 
| 10 | 
            +
                128,
         | 
| 11 | 
            +
                128,
         | 
| 12 | 
            +
                128
         | 
| 13 | 
            +
              ],
         | 
| 14 | 
            +
              "center_input_sample": false,
         | 
| 15 | 
            +
              "class_embed_type": null,
         | 
| 16 | 
            +
              "class_embeddings_concat": false,
         | 
| 17 | 
            +
              "conv_in_kernel": 3,
         | 
| 18 | 
            +
              "conv_out_kernel": 3,
         | 
| 19 | 
            +
              "cross_attention_dim": 256,
         | 
| 20 | 
            +
              "cross_attention_norm": null,
         | 
| 21 | 
            +
              "down_block_types": [
         | 
| 22 | 
            +
                "DownBlock2D",
         | 
| 23 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 24 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 25 | 
            +
                "DownBlock2D"
         | 
| 26 | 
            +
              ],
         | 
| 27 | 
            +
              "downsample_padding": 1,
         | 
| 28 | 
            +
              "dual_cross_attention": false,
         | 
| 29 | 
            +
              "encoder_hid_dim": null,
         | 
| 30 | 
            +
              "flip_sin_to_cos": true,
         | 
| 31 | 
            +
              "freq_shift": 0,
         | 
| 32 | 
            +
              "in_channels": 3,
         | 
| 33 | 
            +
              "layers_per_block": 2,
         | 
| 34 | 
            +
              "mid_block_only_cross_attention": null,
         | 
| 35 | 
            +
              "mid_block_scale_factor": 1,
         | 
| 36 | 
            +
              "mid_block_type": "UNetMidBlock2DCrossAttn",
         | 
| 37 | 
            +
              "norm_eps": 1e-05,
         | 
| 38 | 
            +
              "norm_num_groups": 32,
         | 
| 39 | 
            +
              "num_class_embeds": null,
         | 
| 40 | 
            +
              "only_cross_attention": false,
         | 
| 41 | 
            +
              "out_channels": 3,
         | 
| 42 | 
            +
              "projection_class_embeddings_input_dim": null,
         | 
| 43 | 
            +
              "resnet_out_scale_factor": 1.0,
         | 
| 44 | 
            +
              "resnet_skip_time_act": false,
         | 
| 45 | 
            +
              "resnet_time_scale_shift": "default",
         | 
| 46 | 
            +
              "sample_size": 256,
         | 
| 47 | 
            +
              "time_cond_proj_dim": null,
         | 
| 48 | 
            +
              "time_embedding_act_fn": null,
         | 
| 49 | 
            +
              "time_embedding_dim": null,
         | 
| 50 | 
            +
              "time_embedding_type": "positional",
         | 
| 51 | 
            +
              "timestep_post_act": null,
         | 
| 52 | 
            +
              "up_block_types": [
         | 
| 53 | 
            +
                "UpBlock2D",
         | 
| 54 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 55 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 56 | 
            +
                "UpBlock2D"
         | 
| 57 | 
            +
              ],
         | 
| 58 | 
            +
              "upcast_attention": false,
         | 
| 59 | 
            +
              "use_linear_projection": false
         | 
| 60 | 
            +
            }
         | 
    	
        checkpoint-11000/unet/diffusion_pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:e1158d86c311765e5f384876362976c933cae0c14a61c62dead56bd20de8de13
         | 
| 3 | 
            +
            size 63003985
         | 
    	
        checkpoint-11000/unet_ema/config.json
    ADDED
    
    | @@ -0,0 +1,67 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_class_name": "UNet2DConditionModel",
         | 
| 3 | 
            +
              "_diffusers_version": "0.16.1",
         | 
| 4 | 
            +
              "act_fn": "silu",
         | 
| 5 | 
            +
              "addition_embed_type": null,
         | 
| 6 | 
            +
              "addition_embed_type_num_heads": 64,
         | 
| 7 | 
            +
              "attention_head_dim": 8,
         | 
| 8 | 
            +
              "block_out_channels": [
         | 
| 9 | 
            +
                128,
         | 
| 10 | 
            +
                128,
         | 
| 11 | 
            +
                128,
         | 
| 12 | 
            +
                128
         | 
| 13 | 
            +
              ],
         | 
| 14 | 
            +
              "center_input_sample": false,
         | 
| 15 | 
            +
              "class_embed_type": null,
         | 
| 16 | 
            +
              "class_embeddings_concat": false,
         | 
| 17 | 
            +
              "conv_in_kernel": 3,
         | 
| 18 | 
            +
              "conv_out_kernel": 3,
         | 
| 19 | 
            +
              "cross_attention_dim": 256,
         | 
| 20 | 
            +
              "cross_attention_norm": null,
         | 
| 21 | 
            +
              "decay": 0.9999,
         | 
| 22 | 
            +
              "down_block_types": [
         | 
| 23 | 
            +
                "DownBlock2D",
         | 
| 24 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 25 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 26 | 
            +
                "DownBlock2D"
         | 
| 27 | 
            +
              ],
         | 
| 28 | 
            +
              "downsample_padding": 1,
         | 
| 29 | 
            +
              "dual_cross_attention": false,
         | 
| 30 | 
            +
              "encoder_hid_dim": null,
         | 
| 31 | 
            +
              "flip_sin_to_cos": true,
         | 
| 32 | 
            +
              "freq_shift": 0,
         | 
| 33 | 
            +
              "in_channels": 3,
         | 
| 34 | 
            +
              "inv_gamma": 1.0,
         | 
| 35 | 
            +
              "layers_per_block": 2,
         | 
| 36 | 
            +
              "mid_block_only_cross_attention": null,
         | 
| 37 | 
            +
              "mid_block_scale_factor": 1,
         | 
| 38 | 
            +
              "mid_block_type": "UNetMidBlock2DCrossAttn",
         | 
| 39 | 
            +
              "min_decay": 0.0,
         | 
| 40 | 
            +
              "norm_eps": 1e-05,
         | 
| 41 | 
            +
              "norm_num_groups": 32,
         | 
| 42 | 
            +
              "num_class_embeds": null,
         | 
| 43 | 
            +
              "only_cross_attention": false,
         | 
| 44 | 
            +
              "optimization_step": 11000,
         | 
| 45 | 
            +
              "out_channels": 3,
         | 
| 46 | 
            +
              "power": 0.75,
         | 
| 47 | 
            +
              "projection_class_embeddings_input_dim": null,
         | 
| 48 | 
            +
              "resnet_out_scale_factor": 1.0,
         | 
| 49 | 
            +
              "resnet_skip_time_act": false,
         | 
| 50 | 
            +
              "resnet_time_scale_shift": "default",
         | 
| 51 | 
            +
              "sample_size": 256,
         | 
| 52 | 
            +
              "time_cond_proj_dim": null,
         | 
| 53 | 
            +
              "time_embedding_act_fn": null,
         | 
| 54 | 
            +
              "time_embedding_dim": null,
         | 
| 55 | 
            +
              "time_embedding_type": "positional",
         | 
| 56 | 
            +
              "timestep_post_act": null,
         | 
| 57 | 
            +
              "up_block_types": [
         | 
| 58 | 
            +
                "UpBlock2D",
         | 
| 59 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 60 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 61 | 
            +
                "UpBlock2D"
         | 
| 62 | 
            +
              ],
         | 
| 63 | 
            +
              "upcast_attention": false,
         | 
| 64 | 
            +
              "update_after_step": 0,
         | 
| 65 | 
            +
              "use_ema_warmup": true,
         | 
| 66 | 
            +
              "use_linear_projection": false
         | 
| 67 | 
            +
            }
         | 
    	
        checkpoint-11000/unet_ema/diffusion_pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:6004117229e7822e06dabb7ac3662dd41a744b85231d2e83d3c450402f0dabb9
         | 
| 3 | 
            +
            size 62996305
         | 
    	
        checkpoint-11500/optimizer.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:fc607468e063f33ac98757094a1f92f9d8f3f1cc7040cadc24e975ef7cc5a9a6
         | 
| 3 | 
            +
            size 126008021
         | 
    	
        checkpoint-11500/random_states_0.pkl
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:f80fcf338a906fa6d8454d4f5f314e61db61dc407cec55ab8774b401f6c6b359
         | 
| 3 | 
            +
            size 14727
         | 
    	
        checkpoint-11500/scaler.pt
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:7fa181fa360d46feed4180ea17c8b6a4a879a9b4231c2e91aff2be20be9076cc
         | 
| 3 | 
            +
            size 557
         | 
    	
        checkpoint-11500/scheduler.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:f809c4c923ded5bc448297b913b98ffd4f4e70922e5ce149c4e420a3b5988e8f
         | 
| 3 | 
            +
            size 563
         | 
    	
        checkpoint-11500/unet/config.json
    ADDED
    
    | @@ -0,0 +1,60 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_class_name": "UNet2DConditionModel",
         | 
| 3 | 
            +
              "_diffusers_version": "0.16.1",
         | 
| 4 | 
            +
              "act_fn": "silu",
         | 
| 5 | 
            +
              "addition_embed_type": null,
         | 
| 6 | 
            +
              "addition_embed_type_num_heads": 64,
         | 
| 7 | 
            +
              "attention_head_dim": 8,
         | 
| 8 | 
            +
              "block_out_channels": [
         | 
| 9 | 
            +
                128,
         | 
| 10 | 
            +
                128,
         | 
| 11 | 
            +
                128,
         | 
| 12 | 
            +
                128
         | 
| 13 | 
            +
              ],
         | 
| 14 | 
            +
              "center_input_sample": false,
         | 
| 15 | 
            +
              "class_embed_type": null,
         | 
| 16 | 
            +
              "class_embeddings_concat": false,
         | 
| 17 | 
            +
              "conv_in_kernel": 3,
         | 
| 18 | 
            +
              "conv_out_kernel": 3,
         | 
| 19 | 
            +
              "cross_attention_dim": 256,
         | 
| 20 | 
            +
              "cross_attention_norm": null,
         | 
| 21 | 
            +
              "down_block_types": [
         | 
| 22 | 
            +
                "DownBlock2D",
         | 
| 23 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 24 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 25 | 
            +
                "DownBlock2D"
         | 
| 26 | 
            +
              ],
         | 
| 27 | 
            +
              "downsample_padding": 1,
         | 
| 28 | 
            +
              "dual_cross_attention": false,
         | 
| 29 | 
            +
              "encoder_hid_dim": null,
         | 
| 30 | 
            +
              "flip_sin_to_cos": true,
         | 
| 31 | 
            +
              "freq_shift": 0,
         | 
| 32 | 
            +
              "in_channels": 3,
         | 
| 33 | 
            +
              "layers_per_block": 2,
         | 
| 34 | 
            +
              "mid_block_only_cross_attention": null,
         | 
| 35 | 
            +
              "mid_block_scale_factor": 1,
         | 
| 36 | 
            +
              "mid_block_type": "UNetMidBlock2DCrossAttn",
         | 
| 37 | 
            +
              "norm_eps": 1e-05,
         | 
| 38 | 
            +
              "norm_num_groups": 32,
         | 
| 39 | 
            +
              "num_class_embeds": null,
         | 
| 40 | 
            +
              "only_cross_attention": false,
         | 
| 41 | 
            +
              "out_channels": 3,
         | 
| 42 | 
            +
              "projection_class_embeddings_input_dim": null,
         | 
| 43 | 
            +
              "resnet_out_scale_factor": 1.0,
         | 
| 44 | 
            +
              "resnet_skip_time_act": false,
         | 
| 45 | 
            +
              "resnet_time_scale_shift": "default",
         | 
| 46 | 
            +
              "sample_size": 256,
         | 
| 47 | 
            +
              "time_cond_proj_dim": null,
         | 
| 48 | 
            +
              "time_embedding_act_fn": null,
         | 
| 49 | 
            +
              "time_embedding_dim": null,
         | 
| 50 | 
            +
              "time_embedding_type": "positional",
         | 
| 51 | 
            +
              "timestep_post_act": null,
         | 
| 52 | 
            +
              "up_block_types": [
         | 
| 53 | 
            +
                "UpBlock2D",
         | 
| 54 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 55 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 56 | 
            +
                "UpBlock2D"
         | 
| 57 | 
            +
              ],
         | 
| 58 | 
            +
              "upcast_attention": false,
         | 
| 59 | 
            +
              "use_linear_projection": false
         | 
| 60 | 
            +
            }
         | 
    	
        checkpoint-11500/unet/diffusion_pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:e1158d86c311765e5f384876362976c933cae0c14a61c62dead56bd20de8de13
         | 
| 3 | 
            +
            size 63003985
         | 
    	
        checkpoint-11500/unet_ema/config.json
    ADDED
    
    | @@ -0,0 +1,67 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_class_name": "UNet2DConditionModel",
         | 
| 3 | 
            +
              "_diffusers_version": "0.16.1",
         | 
| 4 | 
            +
              "act_fn": "silu",
         | 
| 5 | 
            +
              "addition_embed_type": null,
         | 
| 6 | 
            +
              "addition_embed_type_num_heads": 64,
         | 
| 7 | 
            +
              "attention_head_dim": 8,
         | 
| 8 | 
            +
              "block_out_channels": [
         | 
| 9 | 
            +
                128,
         | 
| 10 | 
            +
                128,
         | 
| 11 | 
            +
                128,
         | 
| 12 | 
            +
                128
         | 
| 13 | 
            +
              ],
         | 
| 14 | 
            +
              "center_input_sample": false,
         | 
| 15 | 
            +
              "class_embed_type": null,
         | 
| 16 | 
            +
              "class_embeddings_concat": false,
         | 
| 17 | 
            +
              "conv_in_kernel": 3,
         | 
| 18 | 
            +
              "conv_out_kernel": 3,
         | 
| 19 | 
            +
              "cross_attention_dim": 256,
         | 
| 20 | 
            +
              "cross_attention_norm": null,
         | 
| 21 | 
            +
              "decay": 0.9999,
         | 
| 22 | 
            +
              "down_block_types": [
         | 
| 23 | 
            +
                "DownBlock2D",
         | 
| 24 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 25 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 26 | 
            +
                "DownBlock2D"
         | 
| 27 | 
            +
              ],
         | 
| 28 | 
            +
              "downsample_padding": 1,
         | 
| 29 | 
            +
              "dual_cross_attention": false,
         | 
| 30 | 
            +
              "encoder_hid_dim": null,
         | 
| 31 | 
            +
              "flip_sin_to_cos": true,
         | 
| 32 | 
            +
              "freq_shift": 0,
         | 
| 33 | 
            +
              "in_channels": 3,
         | 
| 34 | 
            +
              "inv_gamma": 1.0,
         | 
| 35 | 
            +
              "layers_per_block": 2,
         | 
| 36 | 
            +
              "mid_block_only_cross_attention": null,
         | 
| 37 | 
            +
              "mid_block_scale_factor": 1,
         | 
| 38 | 
            +
              "mid_block_type": "UNetMidBlock2DCrossAttn",
         | 
| 39 | 
            +
              "min_decay": 0.0,
         | 
| 40 | 
            +
              "norm_eps": 1e-05,
         | 
| 41 | 
            +
              "norm_num_groups": 32,
         | 
| 42 | 
            +
              "num_class_embeds": null,
         | 
| 43 | 
            +
              "only_cross_attention": false,
         | 
| 44 | 
            +
              "optimization_step": 11500,
         | 
| 45 | 
            +
              "out_channels": 3,
         | 
| 46 | 
            +
              "power": 0.75,
         | 
| 47 | 
            +
              "projection_class_embeddings_input_dim": null,
         | 
| 48 | 
            +
              "resnet_out_scale_factor": 1.0,
         | 
| 49 | 
            +
              "resnet_skip_time_act": false,
         | 
| 50 | 
            +
              "resnet_time_scale_shift": "default",
         | 
| 51 | 
            +
              "sample_size": 256,
         | 
| 52 | 
            +
              "time_cond_proj_dim": null,
         | 
| 53 | 
            +
              "time_embedding_act_fn": null,
         | 
| 54 | 
            +
              "time_embedding_dim": null,
         | 
| 55 | 
            +
              "time_embedding_type": "positional",
         | 
| 56 | 
            +
              "timestep_post_act": null,
         | 
| 57 | 
            +
              "up_block_types": [
         | 
| 58 | 
            +
                "UpBlock2D",
         | 
| 59 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 60 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 61 | 
            +
                "UpBlock2D"
         | 
| 62 | 
            +
              ],
         | 
| 63 | 
            +
              "upcast_attention": false,
         | 
| 64 | 
            +
              "update_after_step": 0,
         | 
| 65 | 
            +
              "use_ema_warmup": true,
         | 
| 66 | 
            +
              "use_linear_projection": false
         | 
| 67 | 
            +
            }
         | 
    	
        checkpoint-11500/unet_ema/diffusion_pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:9eedfd6f6b326c525e67f904217a8eafadfcde751cef42d2db7c7a93408de28a
         | 
| 3 | 
            +
            size 62996305
         | 
    	
        checkpoint-12000/optimizer.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:a3380c2f30a81a02d88838efa9e8be25010083799d69e55749b0dbf355a93c93
         | 
| 3 | 
            +
            size 126008021
         | 
    	
        checkpoint-12000/random_states_0.pkl
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:0333b197630cbf42f4daf53a7c34761da13c0b0a85b16a257dfd4b77c9293c33
         | 
| 3 | 
            +
            size 14727
         | 
    	
        checkpoint-12000/scaler.pt
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:7fa181fa360d46feed4180ea17c8b6a4a879a9b4231c2e91aff2be20be9076cc
         | 
| 3 | 
            +
            size 557
         | 
    	
        checkpoint-12000/scheduler.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:cdb71a91ca2d955f0d9cf47c9afe50f8b92092d141b2aec0b57952f7f34c1cfa
         | 
| 3 | 
            +
            size 563
         | 
    	
        checkpoint-12000/unet/config.json
    ADDED
    
    | @@ -0,0 +1,60 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_class_name": "UNet2DConditionModel",
         | 
| 3 | 
            +
              "_diffusers_version": "0.16.1",
         | 
| 4 | 
            +
              "act_fn": "silu",
         | 
| 5 | 
            +
              "addition_embed_type": null,
         | 
| 6 | 
            +
              "addition_embed_type_num_heads": 64,
         | 
| 7 | 
            +
              "attention_head_dim": 8,
         | 
| 8 | 
            +
              "block_out_channels": [
         | 
| 9 | 
            +
                128,
         | 
| 10 | 
            +
                128,
         | 
| 11 | 
            +
                128,
         | 
| 12 | 
            +
                128
         | 
| 13 | 
            +
              ],
         | 
| 14 | 
            +
              "center_input_sample": false,
         | 
| 15 | 
            +
              "class_embed_type": null,
         | 
| 16 | 
            +
              "class_embeddings_concat": false,
         | 
| 17 | 
            +
              "conv_in_kernel": 3,
         | 
| 18 | 
            +
              "conv_out_kernel": 3,
         | 
| 19 | 
            +
              "cross_attention_dim": 256,
         | 
| 20 | 
            +
              "cross_attention_norm": null,
         | 
| 21 | 
            +
              "down_block_types": [
         | 
| 22 | 
            +
                "DownBlock2D",
         | 
| 23 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 24 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 25 | 
            +
                "DownBlock2D"
         | 
| 26 | 
            +
              ],
         | 
| 27 | 
            +
              "downsample_padding": 1,
         | 
| 28 | 
            +
              "dual_cross_attention": false,
         | 
| 29 | 
            +
              "encoder_hid_dim": null,
         | 
| 30 | 
            +
              "flip_sin_to_cos": true,
         | 
| 31 | 
            +
              "freq_shift": 0,
         | 
| 32 | 
            +
              "in_channels": 3,
         | 
| 33 | 
            +
              "layers_per_block": 2,
         | 
| 34 | 
            +
              "mid_block_only_cross_attention": null,
         | 
| 35 | 
            +
              "mid_block_scale_factor": 1,
         | 
| 36 | 
            +
              "mid_block_type": "UNetMidBlock2DCrossAttn",
         | 
| 37 | 
            +
              "norm_eps": 1e-05,
         | 
| 38 | 
            +
              "norm_num_groups": 32,
         | 
| 39 | 
            +
              "num_class_embeds": null,
         | 
| 40 | 
            +
              "only_cross_attention": false,
         | 
| 41 | 
            +
              "out_channels": 3,
         | 
| 42 | 
            +
              "projection_class_embeddings_input_dim": null,
         | 
| 43 | 
            +
              "resnet_out_scale_factor": 1.0,
         | 
| 44 | 
            +
              "resnet_skip_time_act": false,
         | 
| 45 | 
            +
              "resnet_time_scale_shift": "default",
         | 
| 46 | 
            +
              "sample_size": 256,
         | 
| 47 | 
            +
              "time_cond_proj_dim": null,
         | 
| 48 | 
            +
              "time_embedding_act_fn": null,
         | 
| 49 | 
            +
              "time_embedding_dim": null,
         | 
| 50 | 
            +
              "time_embedding_type": "positional",
         | 
| 51 | 
            +
              "timestep_post_act": null,
         | 
| 52 | 
            +
              "up_block_types": [
         | 
| 53 | 
            +
                "UpBlock2D",
         | 
| 54 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 55 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 56 | 
            +
                "UpBlock2D"
         | 
| 57 | 
            +
              ],
         | 
| 58 | 
            +
              "upcast_attention": false,
         | 
| 59 | 
            +
              "use_linear_projection": false
         | 
| 60 | 
            +
            }
         | 
    	
        checkpoint-12000/unet/diffusion_pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:e1158d86c311765e5f384876362976c933cae0c14a61c62dead56bd20de8de13
         | 
| 3 | 
            +
            size 63003985
         | 
    	
        checkpoint-12000/unet_ema/config.json
    ADDED
    
    | @@ -0,0 +1,67 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_class_name": "UNet2DConditionModel",
         | 
| 3 | 
            +
              "_diffusers_version": "0.16.1",
         | 
| 4 | 
            +
              "act_fn": "silu",
         | 
| 5 | 
            +
              "addition_embed_type": null,
         | 
| 6 | 
            +
              "addition_embed_type_num_heads": 64,
         | 
| 7 | 
            +
              "attention_head_dim": 8,
         | 
| 8 | 
            +
              "block_out_channels": [
         | 
| 9 | 
            +
                128,
         | 
| 10 | 
            +
                128,
         | 
| 11 | 
            +
                128,
         | 
| 12 | 
            +
                128
         | 
| 13 | 
            +
              ],
         | 
| 14 | 
            +
              "center_input_sample": false,
         | 
| 15 | 
            +
              "class_embed_type": null,
         | 
| 16 | 
            +
              "class_embeddings_concat": false,
         | 
| 17 | 
            +
              "conv_in_kernel": 3,
         | 
| 18 | 
            +
              "conv_out_kernel": 3,
         | 
| 19 | 
            +
              "cross_attention_dim": 256,
         | 
| 20 | 
            +
              "cross_attention_norm": null,
         | 
| 21 | 
            +
              "decay": 0.9999,
         | 
| 22 | 
            +
              "down_block_types": [
         | 
| 23 | 
            +
                "DownBlock2D",
         | 
| 24 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 25 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 26 | 
            +
                "DownBlock2D"
         | 
| 27 | 
            +
              ],
         | 
| 28 | 
            +
              "downsample_padding": 1,
         | 
| 29 | 
            +
              "dual_cross_attention": false,
         | 
| 30 | 
            +
              "encoder_hid_dim": null,
         | 
| 31 | 
            +
              "flip_sin_to_cos": true,
         | 
| 32 | 
            +
              "freq_shift": 0,
         | 
| 33 | 
            +
              "in_channels": 3,
         | 
| 34 | 
            +
              "inv_gamma": 1.0,
         | 
| 35 | 
            +
              "layers_per_block": 2,
         | 
| 36 | 
            +
              "mid_block_only_cross_attention": null,
         | 
| 37 | 
            +
              "mid_block_scale_factor": 1,
         | 
| 38 | 
            +
              "mid_block_type": "UNetMidBlock2DCrossAttn",
         | 
| 39 | 
            +
              "min_decay": 0.0,
         | 
| 40 | 
            +
              "norm_eps": 1e-05,
         | 
| 41 | 
            +
              "norm_num_groups": 32,
         | 
| 42 | 
            +
              "num_class_embeds": null,
         | 
| 43 | 
            +
              "only_cross_attention": false,
         | 
| 44 | 
            +
              "optimization_step": 12000,
         | 
| 45 | 
            +
              "out_channels": 3,
         | 
| 46 | 
            +
              "power": 0.75,
         | 
| 47 | 
            +
              "projection_class_embeddings_input_dim": null,
         | 
| 48 | 
            +
              "resnet_out_scale_factor": 1.0,
         | 
| 49 | 
            +
              "resnet_skip_time_act": false,
         | 
| 50 | 
            +
              "resnet_time_scale_shift": "default",
         | 
| 51 | 
            +
              "sample_size": 256,
         | 
| 52 | 
            +
              "time_cond_proj_dim": null,
         | 
| 53 | 
            +
              "time_embedding_act_fn": null,
         | 
| 54 | 
            +
              "time_embedding_dim": null,
         | 
| 55 | 
            +
              "time_embedding_type": "positional",
         | 
| 56 | 
            +
              "timestep_post_act": null,
         | 
| 57 | 
            +
              "up_block_types": [
         | 
| 58 | 
            +
                "UpBlock2D",
         | 
| 59 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 60 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 61 | 
            +
                "UpBlock2D"
         | 
| 62 | 
            +
              ],
         | 
| 63 | 
            +
              "upcast_attention": false,
         | 
| 64 | 
            +
              "update_after_step": 0,
         | 
| 65 | 
            +
              "use_ema_warmup": true,
         | 
| 66 | 
            +
              "use_linear_projection": false
         | 
| 67 | 
            +
            }
         | 
    	
        checkpoint-12000/unet_ema/diffusion_pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:0157acd45e707e424ffa174c7d6606d367dc055b23271715fb0ab38ccf917b9b
         | 
| 3 | 
            +
            size 62996305
         | 
    	
        checkpoint-12500/optimizer.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:74a8377a5e17b3145107e3e0e735f7abe1ca647f89c52701e79c2c7329c18047
         | 
| 3 | 
            +
            size 126008021
         | 
    	
        checkpoint-12500/random_states_0.pkl
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:72da64f6155ffba7894d19ac1c8ea61f0a4542a6e95e8875ee6af722b0e54262
         | 
| 3 | 
            +
            size 14727
         | 
    	
        checkpoint-12500/scaler.pt
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:7fa181fa360d46feed4180ea17c8b6a4a879a9b4231c2e91aff2be20be9076cc
         | 
| 3 | 
            +
            size 557
         | 
    	
        checkpoint-12500/scheduler.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:827cb33f0a92516b727fe6c9ba128218d2a851815d39a4f8111f682d429f1fc6
         | 
| 3 | 
            +
            size 563
         | 
    	
        checkpoint-12500/unet/config.json
    ADDED
    
    | @@ -0,0 +1,60 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_class_name": "UNet2DConditionModel",
         | 
| 3 | 
            +
              "_diffusers_version": "0.16.1",
         | 
| 4 | 
            +
              "act_fn": "silu",
         | 
| 5 | 
            +
              "addition_embed_type": null,
         | 
| 6 | 
            +
              "addition_embed_type_num_heads": 64,
         | 
| 7 | 
            +
              "attention_head_dim": 8,
         | 
| 8 | 
            +
              "block_out_channels": [
         | 
| 9 | 
            +
                128,
         | 
| 10 | 
            +
                128,
         | 
| 11 | 
            +
                128,
         | 
| 12 | 
            +
                128
         | 
| 13 | 
            +
              ],
         | 
| 14 | 
            +
              "center_input_sample": false,
         | 
| 15 | 
            +
              "class_embed_type": null,
         | 
| 16 | 
            +
              "class_embeddings_concat": false,
         | 
| 17 | 
            +
              "conv_in_kernel": 3,
         | 
| 18 | 
            +
              "conv_out_kernel": 3,
         | 
| 19 | 
            +
              "cross_attention_dim": 256,
         | 
| 20 | 
            +
              "cross_attention_norm": null,
         | 
| 21 | 
            +
              "down_block_types": [
         | 
| 22 | 
            +
                "DownBlock2D",
         | 
| 23 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 24 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 25 | 
            +
                "DownBlock2D"
         | 
| 26 | 
            +
              ],
         | 
| 27 | 
            +
              "downsample_padding": 1,
         | 
| 28 | 
            +
              "dual_cross_attention": false,
         | 
| 29 | 
            +
              "encoder_hid_dim": null,
         | 
| 30 | 
            +
              "flip_sin_to_cos": true,
         | 
| 31 | 
            +
              "freq_shift": 0,
         | 
| 32 | 
            +
              "in_channels": 3,
         | 
| 33 | 
            +
              "layers_per_block": 2,
         | 
| 34 | 
            +
              "mid_block_only_cross_attention": null,
         | 
| 35 | 
            +
              "mid_block_scale_factor": 1,
         | 
| 36 | 
            +
              "mid_block_type": "UNetMidBlock2DCrossAttn",
         | 
| 37 | 
            +
              "norm_eps": 1e-05,
         | 
| 38 | 
            +
              "norm_num_groups": 32,
         | 
| 39 | 
            +
              "num_class_embeds": null,
         | 
| 40 | 
            +
              "only_cross_attention": false,
         | 
| 41 | 
            +
              "out_channels": 3,
         | 
| 42 | 
            +
              "projection_class_embeddings_input_dim": null,
         | 
| 43 | 
            +
              "resnet_out_scale_factor": 1.0,
         | 
| 44 | 
            +
              "resnet_skip_time_act": false,
         | 
| 45 | 
            +
              "resnet_time_scale_shift": "default",
         | 
| 46 | 
            +
              "sample_size": 256,
         | 
| 47 | 
            +
              "time_cond_proj_dim": null,
         | 
| 48 | 
            +
              "time_embedding_act_fn": null,
         | 
| 49 | 
            +
              "time_embedding_dim": null,
         | 
| 50 | 
            +
              "time_embedding_type": "positional",
         | 
| 51 | 
            +
              "timestep_post_act": null,
         | 
| 52 | 
            +
              "up_block_types": [
         | 
| 53 | 
            +
                "UpBlock2D",
         | 
| 54 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 55 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 56 | 
            +
                "UpBlock2D"
         | 
| 57 | 
            +
              ],
         | 
| 58 | 
            +
              "upcast_attention": false,
         | 
| 59 | 
            +
              "use_linear_projection": false
         | 
| 60 | 
            +
            }
         | 
    	
        checkpoint-12500/unet/diffusion_pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:e1158d86c311765e5f384876362976c933cae0c14a61c62dead56bd20de8de13
         | 
| 3 | 
            +
            size 63003985
         | 
    	
        checkpoint-12500/unet_ema/config.json
    ADDED
    
    | @@ -0,0 +1,67 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_class_name": "UNet2DConditionModel",
         | 
| 3 | 
            +
              "_diffusers_version": "0.16.1",
         | 
| 4 | 
            +
              "act_fn": "silu",
         | 
| 5 | 
            +
              "addition_embed_type": null,
         | 
| 6 | 
            +
              "addition_embed_type_num_heads": 64,
         | 
| 7 | 
            +
              "attention_head_dim": 8,
         | 
| 8 | 
            +
              "block_out_channels": [
         | 
| 9 | 
            +
                128,
         | 
| 10 | 
            +
                128,
         | 
| 11 | 
            +
                128,
         | 
| 12 | 
            +
                128
         | 
| 13 | 
            +
              ],
         | 
| 14 | 
            +
              "center_input_sample": false,
         | 
| 15 | 
            +
              "class_embed_type": null,
         | 
| 16 | 
            +
              "class_embeddings_concat": false,
         | 
| 17 | 
            +
              "conv_in_kernel": 3,
         | 
| 18 | 
            +
              "conv_out_kernel": 3,
         | 
| 19 | 
            +
              "cross_attention_dim": 256,
         | 
| 20 | 
            +
              "cross_attention_norm": null,
         | 
| 21 | 
            +
              "decay": 0.9999,
         | 
| 22 | 
            +
              "down_block_types": [
         | 
| 23 | 
            +
                "DownBlock2D",
         | 
| 24 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 25 | 
            +
                "CrossAttnDownBlock2D",
         | 
| 26 | 
            +
                "DownBlock2D"
         | 
| 27 | 
            +
              ],
         | 
| 28 | 
            +
              "downsample_padding": 1,
         | 
| 29 | 
            +
              "dual_cross_attention": false,
         | 
| 30 | 
            +
              "encoder_hid_dim": null,
         | 
| 31 | 
            +
              "flip_sin_to_cos": true,
         | 
| 32 | 
            +
              "freq_shift": 0,
         | 
| 33 | 
            +
              "in_channels": 3,
         | 
| 34 | 
            +
              "inv_gamma": 1.0,
         | 
| 35 | 
            +
              "layers_per_block": 2,
         | 
| 36 | 
            +
              "mid_block_only_cross_attention": null,
         | 
| 37 | 
            +
              "mid_block_scale_factor": 1,
         | 
| 38 | 
            +
              "mid_block_type": "UNetMidBlock2DCrossAttn",
         | 
| 39 | 
            +
              "min_decay": 0.0,
         | 
| 40 | 
            +
              "norm_eps": 1e-05,
         | 
| 41 | 
            +
              "norm_num_groups": 32,
         | 
| 42 | 
            +
              "num_class_embeds": null,
         | 
| 43 | 
            +
              "only_cross_attention": false,
         | 
| 44 | 
            +
              "optimization_step": 12500,
         | 
| 45 | 
            +
              "out_channels": 3,
         | 
| 46 | 
            +
              "power": 0.75,
         | 
| 47 | 
            +
              "projection_class_embeddings_input_dim": null,
         | 
| 48 | 
            +
              "resnet_out_scale_factor": 1.0,
         | 
| 49 | 
            +
              "resnet_skip_time_act": false,
         | 
| 50 | 
            +
              "resnet_time_scale_shift": "default",
         | 
| 51 | 
            +
              "sample_size": 256,
         | 
| 52 | 
            +
              "time_cond_proj_dim": null,
         | 
| 53 | 
            +
              "time_embedding_act_fn": null,
         | 
| 54 | 
            +
              "time_embedding_dim": null,
         | 
| 55 | 
            +
              "time_embedding_type": "positional",
         | 
| 56 | 
            +
              "timestep_post_act": null,
         | 
| 57 | 
            +
              "up_block_types": [
         | 
| 58 | 
            +
                "UpBlock2D",
         | 
| 59 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 60 | 
            +
                "CrossAttnUpBlock2D",
         | 
| 61 | 
            +
                "UpBlock2D"
         | 
| 62 | 
            +
              ],
         | 
| 63 | 
            +
              "upcast_attention": false,
         | 
| 64 | 
            +
              "update_after_step": 0,
         | 
| 65 | 
            +
              "use_ema_warmup": true,
         | 
| 66 | 
            +
              "use_linear_projection": false
         | 
| 67 | 
            +
            }
         | 
    	
        checkpoint-12500/unet_ema/diffusion_pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:c6d0c3aec77148aad6b5e594a54b1f11ff0e467853686e30bb644d3fcce90d9f
         | 
| 3 | 
            +
            size 62996305
         | 
    	
        checkpoint-13000/optimizer.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:b2e901613cb3db0eccea4d76bebf04c7c9a52a695b213878902553c4b59acd88
         | 
| 3 | 
            +
            size 126008021
         | 
    	
        checkpoint-13000/random_states_0.pkl
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:1bba5aa6de53a1968c802281b3699f97ff59cbfb204b335a0fc952b819763b89
         | 
| 3 | 
            +
            size 14727
         | 
