End of training

README.md

@@ -0,0 +1,43 @@
+---
+license: creativeml-openrail-m
+library_name: diffusers
+tags:
+- text-to-image
+- dreambooth
+- diffusers-training
+- latent-diffusion
+- latent-diffusion-diffusers
+base_model: CompVis/ldm-text2im-large-256
+inference: true
+instance_prompt: a photo of sks scrap metal
+---
+
+<!-- This model card has been generated automatically according to the information the training script had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+
+# DreamBooth - DaichiT/scrap_metal_model_ldm
+
+This is a dreambooth model derived from CompVis/ldm-text2im-large-256. The weights were trained on a photo of sks scrap metal using [DreamBooth](https://dreambooth.github.io/).
+You can find some example images in the following. 
+
+
+
+DreamBooth for the text encoder was enabled: False.
+
+
+## Intended uses & limitations
+
+#### How to use
+
+```python
+# TODO: add an example code snippet for running this diffusion pipeline
+```
+
+#### Limitations and bias
+
+[TODO: provide examples of latent issues and potential remediations]
+
+## Training details
+
+[TODO: describe the data used to train the model]

bert/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/home/daichit/.cache/huggingface/hub/models--CompVis--ldm-text2im-large-256/snapshots/30de525ca11a880baea4962827fb6cb0bb268955/bert",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "LDMBertModel"
+  ],
+  "attention_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1280,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "head_dim": 64,
+  "init_std": 0.02,
+  "max_position_embeddings": 77,
+  "model_type": "ldmbert",
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "scale_embedding": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 30522
+}

bert/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94930b4de14729ac55c43001b62920336630754af59fd369d6b1f615b3e22e00
+size 1164033612

logs/dreambooth/1713838440.854944/events.out.tfevents.1713838440.sirius.3207575.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6606740ec6b777587d546fc833aea0c1c8836e0841ac35b1b8aa88192e51177f
+size 2771

logs/dreambooth/1713838440.856014/hparams.yml

@@ -0,0 +1,60 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_data_dir: null
+class_labels_conditioning: null
+class_prompt: null
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+instance_data_dir: scrap_metal
+instance_prompt: a photo of sks scrap metal
+learning_rate: 5.0e-06
+local_rank: -1
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_steps: 400
+mixed_precision: null
+num_class_images: 100
+num_train_epochs: 80
+num_validation_images: 4
+offset_noise: false
+output_dir: scrap_metal_model_ldm
+pre_compute_text_embeddings: false
+pretrained_model_name_or_path: CompVis/ldm-text2im-large-256
+prior_generation_precision: null
+prior_loss_weight: 1.0
+push_to_hub: true
+report_to: tensorboard
+resolution: 768
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: null
+set_grads_to_none: false
+skip_save_text_encoder: false
+snr_gamma: null
+text_encoder_use_attention_mask: false
+tokenizer_max_length: null
+tokenizer_name: null
+train_batch_size: 1
+train_text_encoder: false
+use_8bit_adam: false
+validation_prompt: null
+validation_scheduler: DPMSolverMultistepScheduler
+validation_steps: 100
+variant: null
+with_prior_preservation: false

logs/dreambooth/events.out.tfevents.1713838440.sirius.3207575.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f0bc30757e34eaa8664d662af72d4ec23877adad1a9bfced35db9f59d2cbbf
+size 33434

model_index.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "LDMTextToImagePipeline",
+  "_diffusers_version": "0.28.0.dev0",
+  "_name_or_path": "CompVis/ldm-text2im-large-256",
+  "bert": [
+    "latent_diffusion",
+    "LDMBertModel"
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "tokenizer": [
+    "transformers",
+    "BertTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vqvae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.28.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": true,
+  "steps_offset": 0,
+  "thresholding": false,
+  "timestep_spacing": "leading",
+  "timestep_values": null,
+  "trained_betas": null
+}

tokenizer/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.28.0.dev0",
+  "_name_or_path": "CompVis/ldm-text2im-large-256",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 1280,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 32,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:736ea2eb872caf6ebab214cb34f979c48fba7a6cbce2a903f2f80983f5b6ed1b
+size 3489285672

vqvae/config.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.28.0.dev0",
+  "_name_or_path": "/home/daichit/.cache/huggingface/hub/models--CompVis--ldm-text2im-large-256/snapshots/30de525ca11a880baea4962827fb6cb0bb268955/vqvae",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 256,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vqvae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4d2b5932bb4151e54e694fd31ccf51fca908223c9485bd56cd0e1d83ad94c49
+size 334643268