Hugging Face's logo

monkseal555
/
katrina12

Diffusers
TensorBoard
Safetensors
StableVideoDiffusionPipeline
Model card Files Metrics Community
monkseal555 commited on
Commit
59f6a96
·
verified ·
1 Parent(s): 5ffd58e

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +36 -0
  2. checkpoint-7000/optimizer.bin +3 -0
  3. checkpoint-7000/random_states_0.pkl +3 -0
  4. checkpoint-7000/scaler.pt +3 -0
  5. checkpoint-7000/scheduler.bin +3 -0
  6. checkpoint-7000/unet/config.json +38 -0
  7. checkpoint-7000/unet/diffusion_pytorch_model.safetensors +3 -0
  8. feature_extractor/preprocessor_config.json +27 -0
  9. image_encoder/config.json +23 -0
  10. image_encoder/model.safetensors +3 -0
  11. logs/SVDXtend/1709740293.291063/events.out.tfevents.1709740293.209-20-157-172.3326.1 +3 -0
  12. logs/SVDXtend/1709740293.2950597/hparams.yml +44 -0
  13. logs/SVDXtend/1709740394.3244843/events.out.tfevents.1709740394.209-20-157-172.4127.1 +3 -0
  14. logs/SVDXtend/1709740394.3272057/hparams.yml +44 -0
  15. logs/SVDXtend/1709740686.6125364/events.out.tfevents.1709740686.209-20-157-172.5191.1 +3 -0
  16. logs/SVDXtend/1709740686.6151733/hparams.yml +44 -0
  17. logs/SVDXtend/1709742316.7998452/events.out.tfevents.1709742316.209-20-157-172.7471.1 +3 -0
  18. logs/SVDXtend/1709742316.802506/hparams.yml +44 -0
  19. logs/SVDXtend/1709743148.813307/events.out.tfevents.1709743148.209-20-157-172.8948.1 +3 -0
  20. logs/SVDXtend/1709743148.815845/hparams.yml +44 -0
  21. logs/SVDXtend/1709744643.132092/events.out.tfevents.1709744643.209-20-157-172.10544.1 +3 -0
  22. logs/SVDXtend/1709744643.1347177/hparams.yml +44 -0
  23. logs/SVDXtend/1709745479.4453015/events.out.tfevents.1709745479.209-20-157-172.12327.1 +3 -0
  24. logs/SVDXtend/1709745479.4478614/hparams.yml +44 -0
  25. logs/SVDXtend/1709746927.173873/events.out.tfevents.1709746927.209-20-157-172.14610.1 +3 -0
  26. logs/SVDXtend/1709746927.1764586/hparams.yml +44 -0
  27. logs/SVDXtend/1709754167.4344592/events.out.tfevents.1709754167.209-20-157-172.26179.1 +3 -0
  28. logs/SVDXtend/1709754167.437661/hparams.yml +44 -0
  29. logs/SVDXtend/1709754287.8160708/events.out.tfevents.1709754287.209-20-157-172.27148.1 +3 -0
  30. logs/SVDXtend/1709754287.8187664/hparams.yml +44 -0
  31. logs/SVDXtend/1709754352.8121934/events.out.tfevents.1709754352.209-20-157-172.27881.1 +3 -0
  32. logs/SVDXtend/1709754352.8148823/hparams.yml +44 -0
  33. logs/SVDXtend/events.out.tfevents.1709740293.209-20-157-172.3326.0 +3 -0
  34. logs/SVDXtend/events.out.tfevents.1709740394.209-20-157-172.4127.0 +3 -0
  35. logs/SVDXtend/events.out.tfevents.1709740686.209-20-157-172.5191.0 +3 -0
  36. logs/SVDXtend/events.out.tfevents.1709742316.209-20-157-172.7471.0 +3 -0
  37. logs/SVDXtend/events.out.tfevents.1709743148.209-20-157-172.8948.0 +3 -0
  38. logs/SVDXtend/events.out.tfevents.1709744643.209-20-157-172.10544.0 +3 -0
  39. logs/SVDXtend/events.out.tfevents.1709745479.209-20-157-172.12327.0 +3 -0
  40. logs/SVDXtend/events.out.tfevents.1709746927.209-20-157-172.14610.0 +3 -0
  41. logs/SVDXtend/events.out.tfevents.1709754167.209-20-157-172.26179.0 +3 -0
  42. logs/SVDXtend/events.out.tfevents.1709754287.209-20-157-172.27148.0 +3 -0
  43. logs/SVDXtend/events.out.tfevents.1709754352.209-20-157-172.27881.0 +3 -0
  44. model_index.json +25 -0
  45. scheduler/scheduler_config.json +21 -0
  46. unet/config.json +38 -0
  47. unet/diffusion_pytorch_model.safetensors +3 -0
  48. vae/config.json +24 -0
  49. vae/diffusion_pytorch_model.safetensors +3 -0
  50. validation_images/step_1000_val_img_0.gif +3 -0
.gitattributes CHANGED
@@ -33,3 +33,39 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ validation_images/step_1000_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
37
+ validation_images/step_1200_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
38
+ validation_images/step_1400_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
39
+ validation_images/step_1600_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
40
+ validation_images/step_1800_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
41
+ validation_images/step_1_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
42
+ validation_images/step_2000_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
43
+ validation_images/step_200_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
44
+ validation_images/step_2200_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
45
+ validation_images/step_2400_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
46
+ validation_images/step_2600_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
47
+ validation_images/step_2800_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
48
+ validation_images/step_3000_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
49
+ validation_images/step_3200_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
50
+ validation_images/step_3400_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
51
+ validation_images/step_3600_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
52
+ validation_images/step_3800_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
53
+ validation_images/step_4000_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
54
+ validation_images/step_400_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
55
+ validation_images/step_4200_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
56
+ validation_images/step_4400_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
57
+ validation_images/step_4600_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
58
+ validation_images/step_4800_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
59
+ validation_images/step_5000_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
60
+ validation_images/step_5200_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
61
+ validation_images/step_5400_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
62
+ validation_images/step_5600_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
63
+ validation_images/step_5800_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
64
+ validation_images/step_6000_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
65
+ validation_images/step_600_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
66
+ validation_images/step_6200_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
67
+ validation_images/step_6400_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
68
+ validation_images/step_6600_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
69
+ validation_images/step_6800_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
70
+ validation_images/step_7000_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
71
+ validation_images/step_800_val_img_0.gif filter=lfs diff=lfs merge=lfs -text
checkpoint-7000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d81234181925eca7eb7dcaedb25203233b1fb888040710a8fe7e609ff87d7f9d
3
+ size 3181312125
checkpoint-7000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d13866e85fed84b20dcf5c5b89fb00d04a26ce332402f62572e127ebafe2ab
3
+ size 14727
checkpoint-7000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d22aed3a858ee389297b2101bb2ed7ee9e37744f1a1f75273dbdf045d65b041a
3
+ size 557
checkpoint-7000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0e6cbbd05427cb09a990f303190d8f0051084080c856964101f9aea5e481068
3
+ size 563
checkpoint-7000/unet/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNetSpatioTemporalConditionModel",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "stabilityai/stable-video-diffusion-img2vid",
5
+ "addition_time_embed_dim": 256,
6
+ "block_out_channels": [
7
+ 320,
8
+ 640,
9
+ 1280,
10
+ 1280
11
+ ],
12
+ "cross_attention_dim": 1024,
13
+ "down_block_types": [
14
+ "CrossAttnDownBlockSpatioTemporal",
15
+ "CrossAttnDownBlockSpatioTemporal",
16
+ "CrossAttnDownBlockSpatioTemporal",
17
+ "DownBlockSpatioTemporal"
18
+ ],
19
+ "in_channels": 8,
20
+ "layers_per_block": 2,
21
+ "num_attention_heads": [
22
+ 5,
23
+ 10,
24
+ 20,
25
+ 20
26
+ ],
27
+ "num_frames": 14,
28
+ "out_channels": 4,
29
+ "projection_class_embeddings_input_dim": 768,
30
+ "sample_size": 96,
31
+ "transformer_layers_per_block": 1,
32
+ "up_block_types": [
33
+ "UpBlockSpatioTemporal",
34
+ "CrossAttnUpBlockSpatioTemporal",
35
+ "CrossAttnUpBlockSpatioTemporal",
36
+ "CrossAttnUpBlockSpatioTemporal"
37
+ ]
38
+ }
checkpoint-7000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d41bbb31b63c289e26e83c780df75a7667c2f8c6a1b0c48895a135a07a59b4
3
+ size 6098682464
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }
image_encoder/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stabilityai/stable-video-diffusion-img2vid",
3
+ "architectures": [
4
+ "CLIPVisionModelWithProjection"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "dropout": 0.0,
8
+ "hidden_act": "gelu",
9
+ "hidden_size": 1280,
10
+ "image_size": 224,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5120,
14
+ "layer_norm_eps": 1e-05,
15
+ "model_type": "clip_vision_model",
16
+ "num_attention_heads": 16,
17
+ "num_channels": 3,
18
+ "num_hidden_layers": 32,
19
+ "patch_size": 14,
20
+ "projection_dim": 1024,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.38.2"
23
+ }
image_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae616c24393dd1854372b0639e5541666f7521cbe219669255e865cb7f89466a
3
+ size 1264217240
logs/SVDXtend/1709740293.291063/events.out.tfevents.1709740293.209-20-157-172.3326.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aca7dd11ed7b4c627c7216a2e907216bd619a46a54f55f7788ec322c2bc50f6f
3
+ size 2205
logs/SVDXtend/1709740293.2950597/hparams.yml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ checkpointing_steps: 1000
7
+ checkpoints_total_limit: 1
8
+ conditioning_dropout_prob: 0.1
9
+ enable_xformers_memory_efficient_attention: false
10
+ global_batch_size: 1
11
+ gradient_accumulation_steps: 1
12
+ gradient_checkpointing: false
13
+ height: 320
14
+ hub_model_id: null
15
+ hub_token: null
16
+ learning_rate: 1.0e-05
17
+ local_rank: -1
18
+ logging_dir: logs
19
+ lr_scheduler: constant
20
+ lr_warmup_steps: 0
21
+ max_grad_norm: 1.0
22
+ max_train_steps: 5
23
+ mixed_precision: fp16
24
+ non_ema_revision: null
25
+ num_frames: 25
26
+ num_train_epochs: 1
27
+ num_validation_images: 1
28
+ num_workers: 8
29
+ output_dir: ./outputs
30
+ per_gpu_batch_size: 1
31
+ pretrain_unet: null
32
+ pretrained_model_name_or_path: stabilityai/stable-video-diffusion-img2vid
33
+ push_to_hub: false
34
+ rank: 128
35
+ report_to: tensorboard
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: 123
40
+ use_8bit_adam: false
41
+ use_ema: false
42
+ validation_prompt: null
43
+ validation_steps: 200
44
+ width: 512
logs/SVDXtend/1709740394.3244843/events.out.tfevents.1709740394.209-20-157-172.4127.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7950b4187c47e9ace7c45319c1ce3e371eee46999848e9b5cd75dcb469685cac
3
+ size 2205
logs/SVDXtend/1709740394.3272057/hparams.yml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ checkpointing_steps: 1000
7
+ checkpoints_total_limit: 1
8
+ conditioning_dropout_prob: 0.1
9
+ enable_xformers_memory_efficient_attention: false
10
+ global_batch_size: 1
11
+ gradient_accumulation_steps: 1
12
+ gradient_checkpointing: false
13
+ height: 320
14
+ hub_model_id: null
15
+ hub_token: null
16
+ learning_rate: 1.0e-05
17
+ local_rank: -1
18
+ logging_dir: logs
19
+ lr_scheduler: constant
20
+ lr_warmup_steps: 0
21
+ max_grad_norm: 1.0
22
+ max_train_steps: 5
23
+ mixed_precision: fp16
24
+ non_ema_revision: null
25
+ num_frames: 25
26
+ num_train_epochs: 1
27
+ num_validation_images: 1
28
+ num_workers: 8
29
+ output_dir: ./outputs
30
+ per_gpu_batch_size: 1
31
+ pretrain_unet: null
32
+ pretrained_model_name_or_path: stabilityai/stable-video-diffusion-img2vid
33
+ push_to_hub: false
34
+ rank: 128
35
+ report_to: tensorboard
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: 123
40
+ use_8bit_adam: false
41
+ use_ema: false
42
+ validation_prompt: null
43
+ validation_steps: 200
44
+ width: 512
logs/SVDXtend/1709740686.6125364/events.out.tfevents.1709740686.209-20-157-172.5191.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76b2812f5cfea4521a76c57e8308d999b9cfae86c585bb3939739e627923aeff
3
+ size 2205
logs/SVDXtend/1709740686.6151733/hparams.yml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ checkpointing_steps: 1000
7
+ checkpoints_total_limit: 1
8
+ conditioning_dropout_prob: 0.1
9
+ enable_xformers_memory_efficient_attention: false
10
+ global_batch_size: 1
11
+ gradient_accumulation_steps: 1
12
+ gradient_checkpointing: false
13
+ height: 320
14
+ hub_model_id: null
15
+ hub_token: null
16
+ learning_rate: 1.0e-05
17
+ local_rank: -1
18
+ logging_dir: logs
19
+ lr_scheduler: constant
20
+ lr_warmup_steps: 0
21
+ max_grad_norm: 1.0
22
+ max_train_steps: 5
23
+ mixed_precision: fp16
24
+ non_ema_revision: null
25
+ num_frames: 25
26
+ num_train_epochs: 1
27
+ num_validation_images: 1
28
+ num_workers: 8
29
+ output_dir: ./outputs
30
+ per_gpu_batch_size: 1
31
+ pretrain_unet: null
32
+ pretrained_model_name_or_path: stabilityai/stable-video-diffusion-img2vid
33
+ push_to_hub: false
34
+ rank: 128
35
+ report_to: tensorboard
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: 123
40
+ use_8bit_adam: false
41
+ use_ema: false
42
+ validation_prompt: null
43
+ validation_steps: 200
44
+ width: 512
logs/SVDXtend/1709742316.7998452/events.out.tfevents.1709742316.209-20-157-172.7471.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64f9c6e8723253ba0409c2a6c9c1000b569ad32065957168c31fe304207e531b
3
+ size 2205
logs/SVDXtend/1709742316.802506/hparams.yml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ checkpointing_steps: 1000
7
+ checkpoints_total_limit: 1
8
+ conditioning_dropout_prob: 0.1
9
+ enable_xformers_memory_efficient_attention: false
10
+ global_batch_size: 1
11
+ gradient_accumulation_steps: 1
12
+ gradient_checkpointing: false
13
+ height: 320
14
+ hub_model_id: null
15
+ hub_token: null
16
+ learning_rate: 1.0e-05
17
+ local_rank: -1
18
+ logging_dir: logs
19
+ lr_scheduler: constant
20
+ lr_warmup_steps: 0
21
+ max_grad_norm: 1.0
22
+ max_train_steps: 50000
23
+ mixed_precision: fp16
24
+ non_ema_revision: null
25
+ num_frames: 25
26
+ num_train_epochs: 1
27
+ num_validation_images: 1
28
+ num_workers: 8
29
+ output_dir: ./outputs
30
+ per_gpu_batch_size: 1
31
+ pretrain_unet: null
32
+ pretrained_model_name_or_path: stabilityai/stable-video-diffusion-img2vid
33
+ push_to_hub: false
34
+ rank: 128
35
+ report_to: tensorboard
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: 123
40
+ use_8bit_adam: false
41
+ use_ema: false
42
+ validation_prompt: null
43
+ validation_steps: 200
44
+ width: 512
logs/SVDXtend/1709743148.813307/events.out.tfevents.1709743148.209-20-157-172.8948.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28345a733dc211b153880a2b8bf9713772f4df3ee0a9bcec3ee3018f14c07b1d
3
+ size 2205
logs/SVDXtend/1709743148.815845/hparams.yml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ checkpointing_steps: 1000
7
+ checkpoints_total_limit: 1
8
+ conditioning_dropout_prob: 0.1
9
+ enable_xformers_memory_efficient_attention: false
10
+ global_batch_size: 1
11
+ gradient_accumulation_steps: 1
12
+ gradient_checkpointing: false
13
+ height: 320
14
+ hub_model_id: null
15
+ hub_token: null
16
+ learning_rate: 1.0e-05
17
+ local_rank: -1
18
+ logging_dir: logs
19
+ lr_scheduler: constant
20
+ lr_warmup_steps: 0
21
+ max_grad_norm: 1.0
22
+ max_train_steps: 50000
23
+ mixed_precision: fp16
24
+ non_ema_revision: null
25
+ num_frames: 25
26
+ num_train_epochs: 1
27
+ num_validation_images: 1
28
+ num_workers: 8
29
+ output_dir: ./outputs
30
+ per_gpu_batch_size: 1
31
+ pretrain_unet: null
32
+ pretrained_model_name_or_path: stabilityai/stable-video-diffusion-img2vid
33
+ push_to_hub: false
34
+ rank: 128
35
+ report_to: tensorboard
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: 123
40
+ use_8bit_adam: false
41
+ use_ema: false
42
+ validation_prompt: null
43
+ validation_steps: 200
44
+ width: 512
logs/SVDXtend/1709744643.132092/events.out.tfevents.1709744643.209-20-157-172.10544.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29a787b8b6ed3fa2f7f93fa7e772c9d6ffdc6d35f5c110bb64ddb7abb33d9715
3
+ size 2205
logs/SVDXtend/1709744643.1347177/hparams.yml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ checkpointing_steps: 1000
7
+ checkpoints_total_limit: 1
8
+ conditioning_dropout_prob: 0.1
9
+ enable_xformers_memory_efficient_attention: false
10
+ global_batch_size: 1
11
+ gradient_accumulation_steps: 1
12
+ gradient_checkpointing: false
13
+ height: 320
14
+ hub_model_id: null
15
+ hub_token: null
16
+ learning_rate: 1.0e-05
17
+ local_rank: -1
18
+ logging_dir: logs
19
+ lr_scheduler: constant
20
+ lr_warmup_steps: 0
21
+ max_grad_norm: 1.0
22
+ max_train_steps: 50000
23
+ mixed_precision: fp16
24
+ non_ema_revision: null
25
+ num_frames: 25
26
+ num_train_epochs: 1
27
+ num_validation_images: 1
28
+ num_workers: 8
29
+ output_dir: ./outputs
30
+ per_gpu_batch_size: 1
31
+ pretrain_unet: null
32
+ pretrained_model_name_or_path: stabilityai/stable-video-diffusion-img2vid
33
+ push_to_hub: false
34
+ rank: 128
35
+ report_to: tensorboard
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: 123
40
+ use_8bit_adam: false
41
+ use_ema: false
42
+ validation_prompt: null
43
+ validation_steps: 200
44
+ width: 512
logs/SVDXtend/1709745479.4453015/events.out.tfevents.1709745479.209-20-157-172.12327.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c44a5949ae07d27ae762a5ec47c4f859c19b5d6704af90bcea18184830bce12
3
+ size 2205
logs/SVDXtend/1709745479.4478614/hparams.yml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ checkpointing_steps: 1000
7
+ checkpoints_total_limit: 1
8
+ conditioning_dropout_prob: 0.1
9
+ enable_xformers_memory_efficient_attention: false
10
+ global_batch_size: 1
11
+ gradient_accumulation_steps: 1
12
+ gradient_checkpointing: false
13
+ height: 320
14
+ hub_model_id: null
15
+ hub_token: null
16
+ learning_rate: 1.0e-05
17
+ local_rank: -1
18
+ logging_dir: logs
19
+ lr_scheduler: constant
20
+ lr_warmup_steps: 0
21
+ max_grad_norm: 1.0
22
+ max_train_steps: 7000
23
+ mixed_precision: fp16
24
+ non_ema_revision: null
25
+ num_frames: 25
26
+ num_train_epochs: 1
27
+ num_validation_images: 1
28
+ num_workers: 8
29
+ output_dir: ./outputs
30
+ per_gpu_batch_size: 1
31
+ pretrain_unet: null
32
+ pretrained_model_name_or_path: stabilityai/stable-video-diffusion-img2vid
33
+ push_to_hub: false
34
+ rank: 128
35
+ report_to: tensorboard
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: 123
40
+ use_8bit_adam: false
41
+ use_ema: false
42
+ validation_prompt: null
43
+ validation_steps: 200
44
+ width: 512
logs/SVDXtend/1709746927.173873/events.out.tfevents.1709746927.209-20-157-172.14610.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdbbf3951f0784b21863d85a24df2218815ea55760a06c20e7eb9c6ef4c1b1e7
3
+ size 2205
logs/SVDXtend/1709746927.1764586/hparams.yml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ checkpointing_steps: 1000
7
+ checkpoints_total_limit: 1
8
+ conditioning_dropout_prob: 0.1
9
+ enable_xformers_memory_efficient_attention: false
10
+ global_batch_size: 1
11
+ gradient_accumulation_steps: 1
12
+ gradient_checkpointing: false
13
+ height: 320
14
+ hub_model_id: null
15
+ hub_token: null
16
+ learning_rate: 1.0e-05
17
+ local_rank: -1
18
+ logging_dir: logs
19
+ lr_scheduler: constant
20
+ lr_warmup_steps: 0
21
+ max_grad_norm: 1.0
22
+ max_train_steps: 7000
23
+ mixed_precision: fp16
24
+ non_ema_revision: null
25
+ num_frames: 25
26
+ num_train_epochs: 1
27
+ num_validation_images: 1
28
+ num_workers: 8
29
+ output_dir: ./outputs
30
+ per_gpu_batch_size: 1
31
+ pretrain_unet: null
32
+ pretrained_model_name_or_path: stabilityai/stable-video-diffusion-img2vid
33
+ push_to_hub: false
34
+ rank: 128
35
+ report_to: tensorboard
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: 123
40
+ use_8bit_adam: false
41
+ use_ema: false
42
+ validation_prompt: null
43
+ validation_steps: 200
44
+ width: 512
logs/SVDXtend/1709754167.4344592/events.out.tfevents.1709754167.209-20-157-172.26179.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c793546fb6b74af8b2db3f3e5199779796d2110a794a8b026e3a5e512684f30c
3
+ size 2278
logs/SVDXtend/1709754167.437661/hparams.yml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ checkpointing_steps: 1000
7
+ checkpoints_total_limit: 1
8
+ conditioning_dropout_prob: 0.1
9
+ enable_xformers_memory_efficient_attention: false
10
+ global_batch_size: 1
11
+ gradient_accumulation_steps: 1
12
+ gradient_checkpointing: false
13
+ height: 320
14
+ hub_model_id: null
15
+ hub_token: null
16
+ learning_rate: 1.0e-05
17
+ local_rank: -1
18
+ logging_dir: logs
19
+ lr_scheduler: constant
20
+ lr_warmup_steps: 0
21
+ max_grad_norm: 1.0
22
+ max_train_steps: 10000
23
+ mixed_precision: fp16
24
+ non_ema_revision: null
25
+ num_frames: 25
26
+ num_train_epochs: 1
27
+ num_validation_images: 1
28
+ num_workers: 8
29
+ output_dir: ./outputs
30
+ per_gpu_batch_size: 1
31
+ pretrain_unet: null
32
+ pretrained_model_name_or_path: stabilityai/stable-video-diffusion-img2vid
33
+ push_to_hub: false
34
+ rank: 128
35
+ report_to: tensorboard
36
+ resume_from_checkpoint: checkpoint-7000
37
+ revision: null
38
+ scale_lr: false
39
+ seed: 123
40
+ use_8bit_adam: false
41
+ use_ema: false
42
+ validation_prompt: null
43
+ validation_steps: 200
44
+ width: 512
logs/SVDXtend/1709754287.8160708/events.out.tfevents.1709754287.209-20-157-172.27148.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:824dd8bb3a0fe924a3b0287c2db24005b385f9064d0d60171eab117c80b8e713
3
+ size 2278
logs/SVDXtend/1709754287.8187664/hparams.yml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ checkpointing_steps: 1000
7
+ checkpoints_total_limit: 1
8
+ conditioning_dropout_prob: 0.1
9
+ enable_xformers_memory_efficient_attention: false
10
+ global_batch_size: 1
11
+ gradient_accumulation_steps: 1
12
+ gradient_checkpointing: false
13
+ height: 320
14
+ hub_model_id: null
15
+ hub_token: null
16
+ learning_rate: 1.0e-05
17
+ local_rank: -1
18
+ logging_dir: logs
19
+ lr_scheduler: constant
20
+ lr_warmup_steps: 0
21
+ max_grad_norm: 1.0
22
+ max_train_steps: 10000
23
+ mixed_precision: fp16
24
+ non_ema_revision: null
25
+ num_frames: 25
26
+ num_train_epochs: 1
27
+ num_validation_images: 1
28
+ num_workers: 8
29
+ output_dir: ./outputs
30
+ per_gpu_batch_size: 1
31
+ pretrain_unet: null
32
+ pretrained_model_name_or_path: stabilityai/stable-video-diffusion-img2vid
33
+ push_to_hub: false
34
+ rank: 128
35
+ report_to: tensorboard
36
+ resume_from_checkpoint: checkpoint-7000
37
+ revision: null
38
+ scale_lr: false
39
+ seed: 123
40
+ use_8bit_adam: false
41
+ use_ema: false
42
+ validation_prompt: null
43
+ validation_steps: 200
44
+ width: 512
logs/SVDXtend/1709754352.8121934/events.out.tfevents.1709754352.209-20-157-172.27881.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9739df558603cbd4eff0b3ebc57b042171107a0109f5a214d55875abbf7588a
3
+ size 2278
logs/SVDXtend/1709754352.8148823/hparams.yml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ checkpointing_steps: 1000
7
+ checkpoints_total_limit: 1
8
+ conditioning_dropout_prob: 0.1
9
+ enable_xformers_memory_efficient_attention: false
10
+ global_batch_size: 1
11
+ gradient_accumulation_steps: 1
12
+ gradient_checkpointing: false
13
+ height: 320
14
+ hub_model_id: null
15
+ hub_token: null
16
+ learning_rate: 1.0e-05
17
+ local_rank: -1
18
+ logging_dir: logs
19
+ lr_scheduler: constant
20
+ lr_warmup_steps: 0
21
+ max_grad_norm: 1.0
22
+ max_train_steps: 1000
23
+ mixed_precision: fp16
24
+ non_ema_revision: null
25
+ num_frames: 25
26
+ num_train_epochs: 1
27
+ num_validation_images: 1
28
+ num_workers: 8
29
+ output_dir: ./outputs
30
+ per_gpu_batch_size: 1
31
+ pretrain_unet: null
32
+ pretrained_model_name_or_path: stabilityai/stable-video-diffusion-img2vid
33
+ push_to_hub: false
34
+ rank: 128
35
+ report_to: tensorboard
36
+ resume_from_checkpoint: checkpoint-7000
37
+ revision: null
38
+ scale_lr: false
39
+ seed: 123
40
+ use_8bit_adam: false
41
+ use_ema: false
42
+ validation_prompt: null
43
+ validation_steps: 200
44
+ width: 512
logs/SVDXtend/events.out.tfevents.1709740293.209-20-157-172.3326.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf67ec80ed93f45f58b3ee9c9ec03b77b8c1663277df4ce09ae19962c35f6086
3
+ size 136
logs/SVDXtend/events.out.tfevents.1709740394.209-20-157-172.4127.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1de88151e45bac420b272304328c6724850d7ed797f8b48ced9addb598d528b0
3
+ size 136
logs/SVDXtend/events.out.tfevents.1709740686.209-20-157-172.5191.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee6115bc214ebd60bb50ffdc37f281ed1709a9b44fc5e6ce616571ad04bca15c
3
+ size 328
logs/SVDXtend/events.out.tfevents.1709742316.209-20-157-172.7471.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb9d74f8fff1b322b5d0f8d69067a7a79b2b6e20d97310f7fe248a4d700b2a5b
3
+ size 22305
logs/SVDXtend/events.out.tfevents.1709743148.209-20-157-172.8948.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d2749446f3f0cab7468452ee27a7423f1c41c6da6af58756e9b7906027dc501
3
+ size 3208
logs/SVDXtend/events.out.tfevents.1709744643.209-20-157-172.10544.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfa18ee1f9053ab9276b72bbd6f20dad906afaecca0a324b3ae758ea9e728c33
3
+ size 34016
logs/SVDXtend/events.out.tfevents.1709745479.209-20-157-172.12327.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:310f090d71f0703b58ffc7b999c19ead1249031cd952b85a02c2693b5118b597
3
+ size 97961
logs/SVDXtend/events.out.tfevents.1709746927.209-20-157-172.14610.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a19de1440db35af84af7e888f4684ff1f477d437f75012f51e4ecc200bc5d429
3
+ size 342961
logs/SVDXtend/events.out.tfevents.1709754167.209-20-157-172.26179.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22c262118c7a6e39756a5a34a2ad3d371b276b684359e8e6e65378d67843b5ce
3
+ size 88
logs/SVDXtend/events.out.tfevents.1709754287.209-20-157-172.27148.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58a2c632df52fd3cc3dba23abd5a8b7d8bb4baaf3efef516d2601d86df75d395
3
+ size 88
logs/SVDXtend/events.out.tfevents.1709754352.209-20-157-172.27881.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78cd738bb3efe2a9407d9be1eb25b72fa2cb4b691b37246a63d0eb93385d6bce
3
+ size 88
model_index.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableVideoDiffusionPipeline",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "stabilityai/stable-video-diffusion-img2vid",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "image_encoder": [
10
+ "transformers",
11
+ "CLIPVisionModelWithProjection"
12
+ ],
13
+ "scheduler": [
14
+ "diffusers",
15
+ "EulerDiscreteScheduler"
16
+ ],
17
+ "unet": [
18
+ "diffusers",
19
+ "UNetSpatioTemporalConditionModel"
20
+ ],
21
+ "vae": [
22
+ "diffusers",
23
+ "AutoencoderKLTemporalDecoder"
24
+ ]
25
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "EulerDiscreteScheduler",
3
+ "_diffusers_version": "0.26.3",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "interpolation_type": "linear",
9
+ "num_train_timesteps": 1000,
10
+ "prediction_type": "v_prediction",
11
+ "rescale_betas_zero_snr": false,
12
+ "set_alpha_to_one": false,
13
+ "sigma_max": 700.0,
14
+ "sigma_min": 0.002,
15
+ "skip_prk_steps": true,
16
+ "steps_offset": 1,
17
+ "timestep_spacing": "leading",
18
+ "timestep_type": "continuous",
19
+ "trained_betas": null,
20
+ "use_karras_sigmas": true
21
+ }
unet/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNetSpatioTemporalConditionModel",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "stabilityai/stable-video-diffusion-img2vid",
5
+ "addition_time_embed_dim": 256,
6
+ "block_out_channels": [
7
+ 320,
8
+ 640,
9
+ 1280,
10
+ 1280
11
+ ],
12
+ "cross_attention_dim": 1024,
13
+ "down_block_types": [
14
+ "CrossAttnDownBlockSpatioTemporal",
15
+ "CrossAttnDownBlockSpatioTemporal",
16
+ "CrossAttnDownBlockSpatioTemporal",
17
+ "DownBlockSpatioTemporal"
18
+ ],
19
+ "in_channels": 8,
20
+ "layers_per_block": 2,
21
+ "num_attention_heads": [
22
+ 5,
23
+ 10,
24
+ 20,
25
+ 20
26
+ ],
27
+ "num_frames": 14,
28
+ "out_channels": 4,
29
+ "projection_class_embeddings_input_dim": 768,
30
+ "sample_size": 96,
31
+ "transformer_layers_per_block": 1,
32
+ "up_block_types": [
33
+ "UpBlockSpatioTemporal",
34
+ "CrossAttnUpBlockSpatioTemporal",
35
+ "CrossAttnUpBlockSpatioTemporal",
36
+ "CrossAttnUpBlockSpatioTemporal"
37
+ ]
38
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d41bbb31b63c289e26e83c780df75a7667c2f8c6a1b0c48895a135a07a59b4
3
+ size 6098682464
vae/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLTemporalDecoder",
3
+ "_diffusers_version": "0.26.3",
4
+ "_name_or_path": "stabilityai/stable-video-diffusion-img2vid",
5
+ "block_out_channels": [
6
+ 128,
7
+ 256,
8
+ 512,
9
+ 512
10
+ ],
11
+ "down_block_types": [
12
+ "DownEncoderBlock2D",
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D"
16
+ ],
17
+ "force_upcast": true,
18
+ "in_channels": 3,
19
+ "latent_channels": 4,
20
+ "layers_per_block": 2,
21
+ "out_channels": 3,
22
+ "sample_size": 768,
23
+ "scaling_factor": 0.18215
24
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af602cd0eb4ad6086ec94fbf1438dfb1be5ec9ac03fd0215640854e90d6463a3
3
+ size 195531910
validation_images/step_1000_val_img_0.gif ADDED

Git LFS Details

  • SHA256: 07ecdfb4258dbc76ea9e37c6f325faf08645324fb5d364d3cd1a8f127665c01c
  • Pointer size: 132 Bytes
  • Size of remote file: 1.58 MB