haorandai commited on
Commit
641451d
1 Parent(s): ed9cc2c

End of training

Browse files
README.md CHANGED
@@ -8,6 +8,11 @@ tags:
8
  - text-to-image
9
  - diffusers
10
  - diffusers-training
 
 
 
 
 
11
  inference: true
12
  ---
13
 
 
8
  - text-to-image
9
  - diffusers
10
  - diffusers-training
11
+ - stable-diffusion-xl
12
+ - stable-diffusion-xl-diffusers
13
+ - text-to-image
14
+ - diffusers-training
15
+ - diffusers
16
  inference: true
17
  ---
18
 
logs/text2image-fine-tune-sdxl/1727421979.0144987/events.out.tfevents.1727421979.datasec2.engr.uconn.edu.3812690.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e80082cb47714a2a45f70e608cfdad4e03437edae619b0c4b535882e010adca
3
+ size 2810
logs/text2image-fine-tune-sdxl/1727421979.0172353/hparams.yml ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: haorandai/Orange_Mammal_Mice_lr0.01_e0.02_3_with3constraints
14
+ enable_npu_flash_attention: false
15
+ enable_xformers_memory_efficient_attention: false
16
+ gradient_accumulation_steps: 4
17
+ gradient_checkpointing: true
18
+ hub_model_id: null
19
+ hub_token: null
20
+ image_column: image
21
+ learning_rate: 1.0e-05
22
+ local_rank: 0
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 200
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ num_train_epochs: 200
32
+ num_validation_images: 4
33
+ output_dir: /scr/home/biw23007/haoran/finetune_xl_model_color_dir_1e-05_200_withconstraint/haorandai/Orange_Mammal_Mice_lr0.01_e0.02_3_with3constraints/
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
36
+ pretrained_vae_model_name_or_path: null
37
+ proportion_empty_prompts: 0
38
+ push_to_hub: true
39
+ random_flip: true
40
+ report_to: tensorboard
41
+ resolution: 512
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ scale_lr: false
45
+ seed: null
46
+ snr_gamma: null
47
+ timestep_bias_begin: 0
48
+ timestep_bias_end: 1000
49
+ timestep_bias_multiplier: 1.0
50
+ timestep_bias_portion: 0.25
51
+ timestep_bias_strategy: none
52
+ train_batch_size: 1
53
+ train_data_dir: null
54
+ use_8bit_adam: false
55
+ use_ema: true
56
+ validation_epochs: 1
57
+ validation_prompt: null
58
+ variant: null
logs/text2image-fine-tune-sdxl/events.out.tfevents.1727421979.datasec2.engr.uconn.edu.3812690.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2be8949e547c6bd3dd133f9ea486f24a426677d819aac87d9fe560493c3ad841
3
+ size 9761
model_index.json CHANGED
@@ -1,32 +1,36 @@
1
  {
2
- "_class_name": "StableDiffusionPipeline",
3
  "_diffusers_version": "0.31.0.dev0",
4
- "_name_or_path": "CompVis/stable-diffusion-v1-4",
5
  "feature_extractor": [
6
- "transformers",
7
- "CLIPImageProcessor"
8
  ],
 
9
  "image_encoder": [
10
  null,
11
  null
12
  ],
13
- "requires_safety_checker": true,
14
- "safety_checker": [
15
- "stable_diffusion",
16
- "StableDiffusionSafetyChecker"
17
- ],
18
  "scheduler": [
19
  "diffusers",
20
- "PNDMScheduler"
21
  ],
22
  "text_encoder": [
23
  "transformers",
24
  "CLIPTextModel"
25
  ],
 
 
 
 
26
  "tokenizer": [
27
  "transformers",
28
  "CLIPTokenizer"
29
  ],
 
 
 
 
30
  "unet": [
31
  "diffusers",
32
  "UNet2DConditionModel"
 
1
  {
2
+ "_class_name": "StableDiffusionXLPipeline",
3
  "_diffusers_version": "0.31.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
  "feature_extractor": [
6
+ null,
7
+ null
8
  ],
9
+ "force_zeros_for_empty_prompt": true,
10
  "image_encoder": [
11
  null,
12
  null
13
  ],
 
 
 
 
 
14
  "scheduler": [
15
  "diffusers",
16
+ "EulerDiscreteScheduler"
17
  ],
18
  "text_encoder": [
19
  "transformers",
20
  "CLIPTextModel"
21
  ],
22
+ "text_encoder_2": [
23
+ "transformers",
24
+ "CLIPTextModelWithProjection"
25
+ ],
26
  "tokenizer": [
27
  "transformers",
28
  "CLIPTokenizer"
29
  ],
30
+ "tokenizer_2": [
31
+ "transformers",
32
+ "CLIPTokenizer"
33
+ ],
34
  "unet": [
35
  "diffusers",
36
  "UNet2DConditionModel"
scheduler/scheduler_config.json CHANGED
@@ -1,15 +1,23 @@
1
  {
2
- "_class_name": "PNDMScheduler",
3
  "_diffusers_version": "0.31.0.dev0",
4
  "beta_end": 0.012,
5
  "beta_schedule": "scaled_linear",
6
  "beta_start": 0.00085,
7
  "clip_sample": false,
 
 
8
  "num_train_timesteps": 1000,
9
  "prediction_type": "epsilon",
 
 
10
  "set_alpha_to_one": false,
 
 
11
  "skip_prk_steps": true,
12
  "steps_offset": 1,
13
  "timestep_spacing": "leading",
14
- "trained_betas": null
 
 
15
  }
 
1
  {
2
+ "_class_name": "EulerDiscreteScheduler",
3
  "_diffusers_version": "0.31.0.dev0",
4
  "beta_end": 0.012,
5
  "beta_schedule": "scaled_linear",
6
  "beta_start": 0.00085,
7
  "clip_sample": false,
8
+ "final_sigmas_type": "zero",
9
+ "interpolation_type": "linear",
10
  "num_train_timesteps": 1000,
11
  "prediction_type": "epsilon",
12
+ "rescale_betas_zero_snr": false,
13
+ "sample_max_value": 1.0,
14
  "set_alpha_to_one": false,
15
+ "sigma_max": null,
16
+ "sigma_min": null,
17
  "skip_prk_steps": true,
18
  "steps_offset": 1,
19
  "timestep_spacing": "leading",
20
+ "timestep_type": "discrete",
21
+ "trained_betas": null,
22
+ "use_karras_sigmas": false
23
  }
text_encoder/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "CompVis/stable-diffusion-v1-4",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
@@ -18,7 +18,7 @@
18
  "num_attention_heads": 12,
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 1,
21
- "projection_dim": 512,
22
  "torch_dtype": "float16",
23
  "transformers_version": "4.44.2",
24
  "vocab_size": 49408
 
1
  {
2
+ "_name_or_path": "/home/biw23007/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/text_encoder",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
 
18
  "num_attention_heads": 12,
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 1,
21
+ "projection_dim": 768,
22
  "torch_dtype": "float16",
23
  "transformers_version": "4.44.2",
24
  "vocab_size": 49408
text_encoder_2/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/biw23007/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/text_encoder_2",
3
+ "architectures": [
4
+ "CLIPTextModelWithProjection"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_size": 1280,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 5120,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 20,
19
+ "num_hidden_layers": 32,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 1280,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.44.2",
24
+ "vocab_size": 49408
25
+ }
text_encoder_2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
3
+ size 1389382176
tokenizer_2/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_2/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "!",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer_2/tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "!",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49406": {
13
+ "content": "<|startoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "49407": {
21
+ "content": "<|endoftext|>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "bos_token": "<|startoftext|>",
30
+ "clean_up_tokenization_spaces": true,
31
+ "do_lower_case": true,
32
+ "eos_token": "<|endoftext|>",
33
+ "errors": "replace",
34
+ "model_max_length": 77,
35
+ "pad_token": "!",
36
+ "tokenizer_class": "CLIPTokenizer",
37
+ "unk_token": "<|endoftext|>"
38
+ }
tokenizer_2/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json CHANGED
@@ -1,17 +1,20 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.31.0.dev0",
4
- "_name_or_path": "CompVis/stable-diffusion-v1-4",
5
  "act_fn": "silu",
6
- "addition_embed_type": null,
7
  "addition_embed_type_num_heads": 64,
8
- "addition_time_embed_dim": null,
9
- "attention_head_dim": 8,
 
 
 
 
10
  "attention_type": "default",
11
  "block_out_channels": [
12
  320,
13
  640,
14
- 1280,
15
  1280
16
  ],
17
  "center_input_sample": false,
@@ -19,13 +22,12 @@
19
  "class_embeddings_concat": false,
20
  "conv_in_kernel": 3,
21
  "conv_out_kernel": 3,
22
- "cross_attention_dim": 768,
23
  "cross_attention_norm": null,
24
  "down_block_types": [
 
25
  "CrossAttnDownBlock2D",
26
- "CrossAttnDownBlock2D",
27
- "CrossAttnDownBlock2D",
28
- "DownBlock2D"
29
  ],
30
  "downsample_padding": 1,
31
  "dropout": 0.0,
@@ -45,24 +47,27 @@
45
  "num_class_embeds": null,
46
  "only_cross_attention": false,
47
  "out_channels": 4,
48
- "projection_class_embeddings_input_dim": null,
49
  "resnet_out_scale_factor": 1.0,
50
  "resnet_skip_time_act": false,
51
  "resnet_time_scale_shift": "default",
52
  "reverse_transformer_layers_per_block": null,
53
- "sample_size": 64,
54
  "time_cond_proj_dim": null,
55
  "time_embedding_act_fn": null,
56
  "time_embedding_dim": null,
57
  "time_embedding_type": "positional",
58
  "timestep_post_act": null,
59
- "transformer_layers_per_block": 1,
 
 
 
 
60
  "up_block_types": [
61
- "UpBlock2D",
62
  "CrossAttnUpBlock2D",
63
  "CrossAttnUpBlock2D",
64
- "CrossAttnUpBlock2D"
65
  ],
66
- "upcast_attention": false,
67
- "use_linear_projection": false
68
  }
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.31.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
  "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
  "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
  "attention_type": "default",
15
  "block_out_channels": [
16
  320,
17
  640,
 
18
  1280
19
  ],
20
  "center_input_sample": false,
 
22
  "class_embeddings_concat": false,
23
  "conv_in_kernel": 3,
24
  "conv_out_kernel": 3,
25
+ "cross_attention_dim": 2048,
26
  "cross_attention_norm": null,
27
  "down_block_types": [
28
+ "DownBlock2D",
29
  "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D"
 
 
31
  ],
32
  "downsample_padding": 1,
33
  "dropout": 0.0,
 
47
  "num_class_embeds": null,
48
  "only_cross_attention": false,
49
  "out_channels": 4,
50
+ "projection_class_embeddings_input_dim": 2816,
51
  "resnet_out_scale_factor": 1.0,
52
  "resnet_skip_time_act": false,
53
  "resnet_time_scale_shift": "default",
54
  "reverse_transformer_layers_per_block": null,
55
+ "sample_size": 128,
56
  "time_cond_proj_dim": null,
57
  "time_embedding_act_fn": null,
58
  "time_embedding_dim": null,
59
  "time_embedding_type": "positional",
60
  "timestep_post_act": null,
61
+ "transformer_layers_per_block": [
62
+ 1,
63
+ 2,
64
+ 10
65
+ ],
66
  "up_block_types": [
 
67
  "CrossAttnUpBlock2D",
68
  "CrossAttnUpBlock2D",
69
+ "UpBlock2D"
70
  ],
71
+ "upcast_attention": null,
72
+ "use_linear_projection": true
73
  }
unet/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a11dd6d51091b12ae746c2a99c00f6a0d4404568ae5ae94652dab9ad46b71309
3
+ size 9988139160
unet/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dba29ac8e43d479e444ee2d177833a6fffdf70b1f731599793d261d3202162ef
3
+ size 281938304
unet/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
vae/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
  "_diffusers_version": "0.31.0.dev0",
4
- "_name_or_path": "CompVis/stable-diffusion-v1-4",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
@@ -24,8 +24,8 @@
24
  "mid_block_add_attention": true,
25
  "norm_num_groups": 32,
26
  "out_channels": 3,
27
- "sample_size": 512,
28
- "scaling_factor": 0.18215,
29
  "shift_factor": null,
30
  "up_block_types": [
31
  "UpDecoderBlock2D",
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
  "_diffusers_version": "0.31.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
 
24
  "mid_block_add_attention": true,
25
  "norm_num_groups": 32,
26
  "out_channels": 3,
27
+ "sample_size": 1024,
28
+ "scaling_factor": 0.13025,
29
  "shift_factor": null,
30
  "up_block_types": [
31
  "UpDecoderBlock2D",
vae/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
3
  size 167335342
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcb60880a46b63dea58e9bc591abe15f8350bde47b405f9c38f4be70c6161e68
3
  size 167335342