Text-to-Image
Diffusers
StableDiffusionPipeline
Inference Endpoints
malhajar commited on
Commit
1522fe0
1 Parent(s): 0aae4e0

Upload folder using huggingface_hub

Browse files
args.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pretrained_model_name_or_path": "runwayml/stable-diffusion-v1-5",
3
+ "pretrained_vae_name_or_path": "stabilityai/sd-vae-ft-mse",
4
+ "revision": "fp16",
5
+ "tokenizer_name": null,
6
+ "instance_data_dir": null,
7
+ "class_data_dir": null,
8
+ "instance_prompt": null,
9
+ "class_prompt": null,
10
+ "save_sample_prompt": "zwx person",
11
+ "save_sample_negative_prompt": null,
12
+ "n_save_sample": 4,
13
+ "save_guidance_scale": 7.5,
14
+ "save_infer_steps": 20,
15
+ "pad_tokens": false,
16
+ "with_prior_preservation": true,
17
+ "prior_loss_weight": 1.0,
18
+ "num_class_images": 50,
19
+ "output_dir": "/content/stable_diffusion_weights/zwx",
20
+ "seed": 1337,
21
+ "resolution": 512,
22
+ "center_crop": false,
23
+ "train_text_encoder": true,
24
+ "train_batch_size": 1,
25
+ "sample_batch_size": 4,
26
+ "num_train_epochs": 16,
27
+ "max_train_steps": 800,
28
+ "gradient_accumulation_steps": 1,
29
+ "gradient_checkpointing": false,
30
+ "learning_rate": 1e-06,
31
+ "scale_lr": false,
32
+ "lr_scheduler": "constant",
33
+ "lr_warmup_steps": 0,
34
+ "use_8bit_adam": true,
35
+ "adam_beta1": 0.9,
36
+ "adam_beta2": 0.999,
37
+ "adam_weight_decay": 0.01,
38
+ "adam_epsilon": 1e-08,
39
+ "max_grad_norm": 1.0,
40
+ "push_to_hub": true,
41
+ "hub_token": null,
42
+ "hub_model_id": null,
43
+ "logging_dir": "logs",
44
+ "log_interval": 10,
45
+ "save_interval": 10000,
46
+ "save_min_steps": 0,
47
+ "mixed_precision": "fp16",
48
+ "not_cache_latents": false,
49
+ "hflip": false,
50
+ "local_rank": -1,
51
+ "concepts_list": [
52
+ {
53
+ "instance_prompt": "zwx person",
54
+ "class_prompt": "person",
55
+ "instance_data_dir": "/content/data/zwx",
56
+ "class_data_dir": "/content/data/dog"
57
+ }
58
+ ],
59
+ "read_prompts_from_txts": false
60
+ }
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "feature_extractor_type": "CLIPFeatureExtractor",
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "CLIPFeatureExtractor",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 224
27
+ }
28
+ }
model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.15.0.dev0",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPFeatureExtractor"
7
+ ],
8
+ "requires_safety_checker": true,
9
+ "safety_checker": [
10
+ null,
11
+ null
12
+ ],
13
+ "scheduler": [
14
+ "diffusers",
15
+ "PNDMScheduler"
16
+ ],
17
+ "text_encoder": [
18
+ "transformers",
19
+ "CLIPTextModel"
20
+ ],
21
+ "tokenizer": [
22
+ "transformers",
23
+ "CLIPTokenizer"
24
+ ],
25
+ "unet": [
26
+ "diffusers",
27
+ "UNet2DConditionModel"
28
+ ],
29
+ "vae": [
30
+ "diffusers",
31
+ "AutoencoderKL"
32
+ ]
33
+ }
samples/0.png ADDED
samples/1.png ADDED
samples/2.png ADDED
samples/3.png ADDED
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.15.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "clip_sample_range": 1.0,
9
+ "dynamic_thresholding_ratio": 0.995,
10
+ "num_train_timesteps": 1000,
11
+ "prediction_type": "epsilon",
12
+ "sample_max_value": 1.0,
13
+ "set_alpha_to_one": false,
14
+ "skip_prk_steps": true,
15
+ "steps_offset": 1,
16
+ "thresholding": false,
17
+ "trained_betas": null
18
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "runwayml/stable-diffusion-v1-5",
3
+ "architectures": [
4
+ "CLIPTextModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "quick_gelu",
11
+ "hidden_size": 768,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 768,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.32.1",
24
+ "vocab_size": 49408
25
+ }
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e59626820c2f60d43a1e0d14c3eee6c9580bcb57fa69e8506f5694f2e8f07b9
3
+ size 492308829
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/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": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "do_lower_case": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 77,
23
+ "pad_token": "<|endoftext|>",
24
+ "tokenizer_class": "CLIPTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.15.0.dev0",
4
+ "_name_or_path": "runwayml/stable-diffusion-v1-5",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": 8,
7
+ "block_out_channels": [
8
+ 320,
9
+ 640,
10
+ 1280,
11
+ 1280
12
+ ],
13
+ "center_input_sample": false,
14
+ "class_embed_type": null,
15
+ "class_embeddings_concat": false,
16
+ "conv_in_kernel": 3,
17
+ "conv_out_kernel": 3,
18
+ "cross_attention_dim": 768,
19
+ "down_block_types": [
20
+ "CrossAttnDownBlock2D",
21
+ "CrossAttnDownBlock2D",
22
+ "CrossAttnDownBlock2D",
23
+ "DownBlock2D"
24
+ ],
25
+ "downsample_padding": 1,
26
+ "dual_cross_attention": false,
27
+ "flip_sin_to_cos": true,
28
+ "freq_shift": 0,
29
+ "in_channels": 4,
30
+ "layers_per_block": 2,
31
+ "mid_block_scale_factor": 1,
32
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
33
+ "norm_eps": 1e-05,
34
+ "norm_num_groups": 32,
35
+ "num_class_embeds": null,
36
+ "only_cross_attention": false,
37
+ "out_channels": 4,
38
+ "projection_class_embeddings_input_dim": null,
39
+ "resnet_time_scale_shift": "default",
40
+ "sample_size": 64,
41
+ "time_cond_proj_dim": null,
42
+ "time_embedding_type": "positional",
43
+ "timestep_post_act": null,
44
+ "up_block_types": [
45
+ "UpBlock2D",
46
+ "CrossAttnUpBlock2D",
47
+ "CrossAttnUpBlock2D",
48
+ "CrossAttnUpBlock2D"
49
+ ],
50
+ "upcast_attention": false,
51
+ "use_linear_projection": false
52
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b4c9fe909dcddd93d2fd666bdeeed0ff9e4fab78f87c147e74e8b0a0a0e03e0
3
+ size 3438375973
vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.15.0.dev0",
4
+ "_name_or_path": "stabilityai/sd-vae-ft-mse",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "in_channels": 3,
19
+ "latent_channels": 4,
20
+ "layers_per_block": 2,
21
+ "norm_num_groups": 32,
22
+ "out_channels": 3,
23
+ "sample_size": 256,
24
+ "scaling_factor": 0.18215,
25
+ "up_block_types": [
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D"
30
+ ]
31
+ }
vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36bb8e1b54aba3a0914eb35fba13dcb107e9f18d379d1df2158732cd4bf56a94
3
+ size 334711857