End of training

README.md

@@ -0,0 +1,43 @@
+---
+license: creativeml-openrail-m
+library_name: diffusers
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- diffusers
+- textual_inversion
+- diffusers-training
+base_model: CompVis/stable-diffusion-v1-4
+inference: true
+---
+
+<!-- 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. -->
+
+
+# Textual inversion text2image fine-tuning - heale22/chairs_inversion_5e-3_5000steps_largetoken
+These are textual inversion adaption weights for CompVis/stable-diffusion-v1-4. You can find some example images in the following. 
+
+![img_0](./image_0.png)
+![img_1](./image_1.png)
+![img_2](./image_2.png)
+![img_3](./image_3.png)
+
+
+
+## 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]

checkpoint-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ec2410672699cbaffc018f129d6f5bc6d473269519f4de3e030f49f6832132
+size 492268240

checkpoint-5000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3d787522b1b21ba9c87e8065c111ea3ee60fbd000fe73f73a4b56577f4ddf83
+size 303570914

checkpoint-5000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:069dc07709c5d2ee323d4ecef3fed3463a9afbdba2ae32b4ccb72fdfbcd78026
+size 14344

checkpoint-5000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72cf154ed8f41df576b07c1417ba12dd739bc25059daee1076255abd70a8c0c
+size 1000

feature_extractor/preprocessor_config.json

@@ -0,0 +1,44 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_convert_rgb",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

learned_embeds-steps-1000.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73b131086561d0dc1bfd7680a83d78df4b66ee0cc490723bd5f55ef4396803a3
+size 4470

learned_embeds-steps-1500.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d724ed75711690e178231450e8a4fc5dd233a6d7365859eb358d2d6ab9be3e
+size 4470

learned_embeds-steps-2000.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4a775395c867c4f8249cb9ef9ca9fb2bda827e4df51cebe18c884536d107b8
+size 4470

learned_embeds-steps-2500.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62deaf0705f42f2fc99045bd6dccf55b39450502498f6967cb05c7e6feefbad4
+size 4470

learned_embeds-steps-3000.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:791723df62ee5a0942a6f0afe46143385ebd2d4245568f43633aa5ca2d22da12
+size 4470

learned_embeds-steps-3500.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95716adc0fff98d1203ad59d70264945e88af1fc229d4171e201932614d69d02
+size 4470

learned_embeds-steps-4000.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a62376d06c1bf21e1ba4739855a9a14dceee400281cd7b7582316a871e378e
+size 4470

learned_embeds-steps-4500.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0f2280efa700e1a9c65c3843c3903892e5bd3e2e27bd33bdb6f6ad801f61a4c
+size 4470

learned_embeds-steps-500.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc0be4360eb36a8ad3d2be011845fcbeabef449bb942709f3ee41855167f00d2
+size 4465

learned_embeds-steps-5000.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e287a2320127f8487eb6b9232f29e4b74eee31846247de91fdfd533fbeddaf5f
+size 4470

learned_embeds.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc63ec2f87a242079f39e17bdc893ab7f47fa376e948b6bf799bb741d5b2e314
+size 4287

logs/textual_inversion/1718248005.3006983/events.out.tfevents.1718248005.deep-chungus-4.csail.mit.edu.3396959.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51dcd7ea5f07f491f1d7a21b0999dcb6ba9fe3fc00210902cad0d7b7363e1a36
+size 2486

logs/textual_inversion/1718248005.3148541/hparams.yml

@@ -0,0 +1,49 @@
+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: 5000
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+initializer_token: chair
+learnable_property: object
+learning_rate: 0.08
+local_rank: -1
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 5000
+mixed_precision: 'no'
+model_name_unique: null
+no_safe_serialization: true
+num_train_epochs: 88
+num_validation_images: 4
+num_vectors: 1
+output_dir: /mnt/xfs/home/alexh22/erasing/chairs_inversion_5e-3_5000steps_largetoken
+placeholder_token: <al-ex-ch-air>
+pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
+push_to_hub: true
+repeats: 100
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: true
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 4
+train_data_dir: /mnt/xfs/home/alexh22/erasing/chairs
+validation_epochs: null
+validation_prompt: A photo of a <al-ex-ch-air>
+validation_steps: 100
+variant: null

logs/textual_inversion/1718272814.411102/events.out.tfevents.1718272814.deep-chungus-2.csail.mit.edu.2930348.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6a04a8ca2160d2d6d2ac258e39a52dfd158e29baa5bdaeb05297154f4d6afbf
+size 2486

logs/textual_inversion/1718272814.4288785/hparams.yml

@@ -0,0 +1,49 @@
+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: 5000
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+initializer_token: chair
+learnable_property: object
+learning_rate: 0.08
+local_rank: -1
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 5000
+mixed_precision: 'no'
+model_name_unique: null
+no_safe_serialization: true
+num_train_epochs: 88
+num_validation_images: 4
+num_vectors: 1
+output_dir: /mnt/xfs/home/alexh22/erasing/chairs_inversion_5e-3_5000steps_largetoken
+placeholder_token: <al-ex-ch-air>
+pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
+push_to_hub: true
+repeats: 100
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: true
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 4
+train_data_dir: /mnt/xfs/home/alexh22/erasing/chairs
+validation_epochs: null
+validation_prompt: A photo of a <al-ex-ch-air>
+validation_steps: 100
+variant: null

logs/textual_inversion/1718290186.3693223/events.out.tfevents.1718290186.deep-chungus-4.csail.mit.edu.637815.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945b88f721d659a93a08a20fc58af7a6a7f802fd91a12c3619f0383bf14244c6
+size 2550

logs/textual_inversion/1718290186.3836005/hparams.yml

@@ -0,0 +1,49 @@
+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: 5000
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+initializer_token: chair
+learnable_property: object
+learning_rate: 0.08
+local_rank: -1
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 5000
+mixed_precision: 'no'
+model_name_unique: null
+no_safe_serialization: true
+num_train_epochs: 88
+num_validation_images: 4
+num_vectors: 1
+output_dir: /mnt/xfs/home/alexh22/erasing/chairs_inversion_5e-3_5000steps_largetoken
+placeholder_token: <al-ex-ch-air>
+pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
+push_to_hub: true
+repeats: 100
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+save_as_full_pipeline: true
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 4
+train_data_dir: /mnt/xfs/home/alexh22/erasing/chairs
+validation_epochs: null
+validation_prompt: A photo of a <al-ex-ch-air>
+validation_steps: 100
+variant: null

logs/textual_inversion/events.out.tfevents.1718248005.deep-chungus-4.csail.mit.edu.3396959.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:725d215561a72f27e776ed9173de79cd5467b232e98a2043d9848c87cd311cbb
+size 88

logs/textual_inversion/events.out.tfevents.1718272814.deep-chungus-2.csail.mit.edu.2930348.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:410325f28922d21cbcdeed8e7c40ebcfe139d80340d152e1ea8aa17d6ae851ef
+size 26676202

logs/textual_inversion/events.out.tfevents.1718290186.deep-chungus-4.csail.mit.edu.637815.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c949d10502c2c248128aa87ec6d239e3dcc7304760d3faefd77dde6643107d44
+size 85102358

model_index.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.29.0.dev0",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

safety_checker/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/xfs/home/alexh22/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/safety_checker",
+  "architectures": [
+    "StableDiffusionSafetyChecker"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "dropout": 0.0,
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 12
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "vision_config": {
+    "dropout": 0.0,
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14
+  }
+}

safety_checker/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
+size 1215979664

scheduler/scheduler_config.json

@@ -0,0 +1,15 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.29.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "vocab_size": 49409
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ec2410672699cbaffc018f129d6f5bc6d473269519f4de3e030f49f6832132
+size 492268240

tokenizer/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<al-ex-ch-air>": 49408
+}

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49408": {
+      "content": "<al-ex-ch-air>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.29.0.dev0",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "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": 768,
+  "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": 64,
+  "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:d54d1800033f872c2ede03a45de06d176a53146e43bc9bdb81b0429560a07dc9
+size 3438167536

vae/config.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.29.0.dev0",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "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": 512,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.safetensors

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