Hugging Face's logo

streamize
/
leosamsMoonfilmFp16-filmGrain20

Text-to-Image
Diffusers
Safetensors
StableDiffusionPipeline
Inference Endpoints
Model card Files Community
streamize commited on
Commit
2734ff1
•
1 Parent(s): df3a5a3

Upload StableDiffusionPipeline

Browse files
Files changed (10) hide show
  1. feature_extractor/preprocessor_config.json +28 -0
  2. model_index.json +37 -37
  3. scheduler/scheduler_config.json +16 -21
  4. text_encoder/config.json +25 -24
  5. tokenizer/merges.txt +0 -0
  6. tokenizer/special_tokens_map.json +24 -24
  7. tokenizer/tokenizer_config.json +30 -33
  8. tokenizer/vocab.json +0 -0
  9. unet/config.json +67 -67
  10. vae/config.json +36 -33
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": "CLIPImageProcessor",
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 CHANGED
@@ -1,37 +1,37 @@
1
- {
2
- "_class_name": "StableDiffusionPipeline",
3
- "_diffusers_version": "0.28.0.dev0",
4
- "feature_extractor": [
5
- null,
6
- null
7
- ],
8
- "image_encoder": [
9
- null,
10
- null
11
- ],
12
- "requires_safety_checker": true,
13
- "safety_checker": [
14
- null,
15
- null
16
- ],
17
- "scheduler": [
18
- "diffusers",
19
- "DDIMScheduler"
20
- ],
21
- "text_encoder": [
22
- "transformers",
23
- "CLIPTextModel"
24
- ],
25
- "tokenizer": [
26
- "transformers",
27
- "CLIPTokenizer"
28
- ],
29
- "unet": [
30
- "diffusers",
31
- "UNet2DConditionModel"
32
- ],
33
- "vae": [
34
- "diffusers",
35
- "AutoencoderKL"
36
- ]
37
- }
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.29.0",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPImageProcessor"
7
+ ],
8
+ "image_encoder": [
9
+ null,
10
+ null
11
+ ],
12
+ "requires_safety_checker": true,
13
+ "safety_checker": [
14
+ null,
15
+ null
16
+ ],
17
+ "scheduler": [
18
+ "diffusers",
19
+ "EulerAncestralDiscreteScheduler"
20
+ ],
21
+ "text_encoder": [
22
+ "transformers",
23
+ "CLIPTextModel"
24
+ ],
25
+ "tokenizer": [
26
+ "transformers",
27
+ "CLIPTokenizer"
28
+ ],
29
+ "unet": [
30
+ "diffusers",
31
+ "UNet2DConditionModel"
32
+ ],
33
+ "vae": [
34
+ "diffusers",
35
+ "AutoencoderKL"
36
+ ]
37
+ }
scheduler/scheduler_config.json CHANGED
@@ -1,21 +1,16 @@
1
- {
2
- "_class_name": "DDIMScheduler",
3
- "_diffusers_version": "0.28.0.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
- "interpolation_type": "linear",
11
- "num_train_timesteps": 1000,
12
- "prediction_type": "epsilon",
13
- "rescale_betas_zero_snr": false,
14
- "sample_max_value": 1.0,
15
- "set_alpha_to_one": false,
16
- "skip_prk_steps": true,
17
- "steps_offset": 1,
18
- "thresholding": false,
19
- "timestep_spacing": "leading",
20
- "trained_betas": null
21
- }
 
1
+ {
2
+ "_class_name": "EulerAncestralDiscreteScheduler",
3
+ "_diffusers_version": "0.29.0",
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
+ "rescale_betas_zero_snr": false,
11
+ "set_alpha_to_one": false,
12
+ "skip_prk_steps": true,
13
+ "steps_offset": 1,
14
+ "timestep_spacing": "linspace",
15
+ "trained_betas": null
16
+ }
 
 
 
 
 
text_encoder/config.json CHANGED
@@ -1,24 +1,25 @@
1
- {
2
- "architectures": [
3
- "CLIPTextModel"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 0,
7
- "dropout": 0.0,
8
- "eos_token_id": 2,
9
- "hidden_act": "quick_gelu",
10
- "hidden_size": 768,
11
- "initializer_factor": 1.0,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 3072,
14
- "layer_norm_eps": 1e-05,
15
- "max_position_embeddings": 77,
16
- "model_type": "clip_text_model",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
- "pad_token_id": 1,
20
- "projection_dim": 768,
21
- "torch_dtype": "float16",
22
- "transformers_version": "4.33.3",
23
- "vocab_size": 49408
24
- }
 
 
1
+ {
2
+ "_name_or_path": "openai/clip-vit-large-patch14",
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": "float16",
23
+ "transformers_version": "4.36.2",
24
+ "vocab_size": 49408
25
+ }
tokenizer/merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json CHANGED
@@ -1,24 +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
- }
 
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 CHANGED
@@ -1,33 +1,30 @@
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
- }
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49406": {
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|startoftext|>",
22
+ "clean_up_tokenization_spaces": true,
23
+ "do_lower_case": true,
24
+ "eos_token": "<|endoftext|>",
25
+ "errors": "replace",
26
+ "model_max_length": 77,
27
+ "pad_token": "<|endoftext|>",
28
+ "tokenizer_class": "CLIPTokenizer",
29
+ "unk_token": "<|endoftext|>"
30
+ }
 
 
 
tokenizer/vocab.json CHANGED
The diff for this file is too large to render. See raw diff
 
unet/config.json CHANGED
@@ -1,67 +1,67 @@
1
- {
2
- "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.28.0.dev0",
4
- "act_fn": "silu",
5
- "addition_embed_type": null,
6
- "addition_embed_type_num_heads": 64,
7
- "addition_time_embed_dim": null,
8
- "attention_head_dim": 8,
9
- "attention_type": "default",
10
- "block_out_channels": [
11
- 320,
12
- 640,
13
- 1280,
14
- 1280
15
- ],
16
- "center_input_sample": false,
17
- "class_embed_type": null,
18
- "class_embeddings_concat": false,
19
- "conv_in_kernel": 3,
20
- "conv_out_kernel": 3,
21
- "cross_attention_dim": 768,
22
- "cross_attention_norm": null,
23
- "down_block_types": [
24
- "CrossAttnDownBlock2D",
25
- "CrossAttnDownBlock2D",
26
- "CrossAttnDownBlock2D",
27
- "DownBlock2D"
28
- ],
29
- "downsample_padding": 1,
30
- "dropout": 0.0,
31
- "dual_cross_attention": false,
32
- "encoder_hid_dim": null,
33
- "encoder_hid_dim_type": null,
34
- "flip_sin_to_cos": true,
35
- "freq_shift": 0,
36
- "in_channels": 4,
37
- "layers_per_block": 2,
38
- "mid_block_only_cross_attention": null,
39
- "mid_block_scale_factor": 1,
40
- "mid_block_type": "UNetMidBlock2DCrossAttn",
41
- "norm_eps": 1e-05,
42
- "norm_num_groups": 32,
43
- "num_attention_heads": null,
44
- "num_class_embeds": null,
45
- "only_cross_attention": false,
46
- "out_channels": 4,
47
- "projection_class_embeddings_input_dim": null,
48
- "resnet_out_scale_factor": 1.0,
49
- "resnet_skip_time_act": false,
50
- "resnet_time_scale_shift": "default",
51
- "reverse_transformer_layers_per_block": null,
52
- "sample_size": 64,
53
- "time_cond_proj_dim": null,
54
- "time_embedding_act_fn": null,
55
- "time_embedding_dim": null,
56
- "time_embedding_type": "positional",
57
- "timestep_post_act": null,
58
- "transformer_layers_per_block": 1,
59
- "up_block_types": [
60
- "UpBlock2D",
61
- "CrossAttnUpBlock2D",
62
- "CrossAttnUpBlock2D",
63
- "CrossAttnUpBlock2D"
64
- ],
65
- "upcast_attention": false,
66
- "use_linear_projection": false
67
- }
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.29.0",
4
+ "act_fn": "silu",
5
+ "addition_embed_type": null,
6
+ "addition_embed_type_num_heads": 64,
7
+ "addition_time_embed_dim": null,
8
+ "attention_head_dim": 8,
9
+ "attention_type": "default",
10
+ "block_out_channels": [
11
+ 320,
12
+ 640,
13
+ 1280,
14
+ 1280
15
+ ],
16
+ "center_input_sample": false,
17
+ "class_embed_type": null,
18
+ "class_embeddings_concat": false,
19
+ "conv_in_kernel": 3,
20
+ "conv_out_kernel": 3,
21
+ "cross_attention_dim": 768,
22
+ "cross_attention_norm": null,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dropout": 0.0,
31
+ "dual_cross_attention": false,
32
+ "encoder_hid_dim": null,
33
+ "encoder_hid_dim_type": null,
34
+ "flip_sin_to_cos": true,
35
+ "freq_shift": 0,
36
+ "in_channels": 4,
37
+ "layers_per_block": 2,
38
+ "mid_block_only_cross_attention": null,
39
+ "mid_block_scale_factor": 1,
40
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
41
+ "norm_eps": 1e-05,
42
+ "norm_num_groups": 32,
43
+ "num_attention_heads": null,
44
+ "num_class_embeds": null,
45
+ "only_cross_attention": false,
46
+ "out_channels": 4,
47
+ "projection_class_embeddings_input_dim": null,
48
+ "resnet_out_scale_factor": 1.0,
49
+ "resnet_skip_time_act": false,
50
+ "resnet_time_scale_shift": "default",
51
+ "reverse_transformer_layers_per_block": null,
52
+ "sample_size": 64,
53
+ "time_cond_proj_dim": null,
54
+ "time_embedding_act_fn": null,
55
+ "time_embedding_dim": null,
56
+ "time_embedding_type": "positional",
57
+ "timestep_post_act": null,
58
+ "transformer_layers_per_block": 1,
59
+ "up_block_types": [
60
+ "UpBlock2D",
61
+ "CrossAttnUpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D"
64
+ ],
65
+ "upcast_attention": false,
66
+ "use_linear_projection": false
67
+ }
vae/config.json CHANGED
@@ -1,33 +1,36 @@
1
- {
2
- "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.28.0.dev0",
4
- "act_fn": "silu",
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
- "latents_mean": null,
21
- "latents_std": null,
22
- "layers_per_block": 2,
23
- "norm_num_groups": 32,
24
- "out_channels": 3,
25
- "sample_size": 512,
26
- "scaling_factor": 0.18215,
27
- "up_block_types": [
28
- "UpDecoderBlock2D",
29
- "UpDecoderBlock2D",
30
- "UpDecoderBlock2D",
31
- "UpDecoderBlock2D"
32
- ]
33
- }
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.29.0",
4
+ "act_fn": "silu",
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
+ "latents_mean": null,
21
+ "latents_std": null,
22
+ "layers_per_block": 2,
23
+ "norm_num_groups": 32,
24
+ "out_channels": 3,
25
+ "sample_size": 512,
26
+ "scaling_factor": 0.18215,
27
+ "shift_factor": null,
28
+ "up_block_types": [
29
+ "UpDecoderBlock2D",
30
+ "UpDecoderBlock2D",
31
+ "UpDecoderBlock2D",
32
+ "UpDecoderBlock2D"
33
+ ],
34
+ "use_post_quant_conv": true,
35
+ "use_quant_conv": true
36
+ }