Text-to-Image
Diffusers
Safetensors
StableDiffusionPipeline
stable-diffusion
Inference Endpoints
hugfacedevolve commited on
Commit
8a3ae26
1 Parent(s): 5cae40e

Adding `diffusers` weights of this model

Browse files

This PR adds fp32 and fp16 weights in PyTorch and safetensors format to stabilityai/stable-diffusion-2-1

model_index.json CHANGED
@@ -1,18 +1,22 @@
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
- "_diffusers_version": "0.8.0",
4
  "feature_extractor": [
5
- "transformers",
6
- "CLIPImageProcessor"
 
 
 
 
7
  ],
8
- "requires_safety_checker": false,
9
  "safety_checker": [
10
  null,
11
  null
12
  ],
13
  "scheduler": [
14
  "diffusers",
15
- "DDIMScheduler"
16
  ],
17
  "text_encoder": [
18
  "transformers",
 
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.27.0.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
+ "DPMSolverMultistepScheduler"
20
  ],
21
  "text_encoder": [
22
  "transformers",
scheduler/scheduler_config.json CHANGED
@@ -1,14 +1,27 @@
1
  {
2
- "_class_name": "DDIMScheduler",
3
- "_diffusers_version": "0.8.0",
 
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": "v_prediction",
 
10
  "set_alpha_to_one": false,
11
- "skip_prk_steps": true,
 
12
  "steps_offset": 1,
13
- "trained_betas": null
 
 
 
 
 
14
  }
 
1
  {
2
+ "_class_name": "DPMSolverMultistepScheduler",
3
+ "_diffusers_version": "0.27.0.dev0",
4
+ "algorithm_type": "dpmsolver++",
5
  "beta_end": 0.012,
6
  "beta_schedule": "scaled_linear",
7
  "beta_start": 0.00085,
8
  "clip_sample": false,
9
+ "dynamic_thresholding_ratio": 0.995,
10
+ "euler_at_final": false,
11
+ "final_sigmas_type": "zero",
12
+ "lambda_min_clipped": -Infinity,
13
+ "lower_order_final": true,
14
  "num_train_timesteps": 1000,
15
+ "prediction_type": "epsilon",
16
+ "sample_max_value": 1.0,
17
  "set_alpha_to_one": false,
18
+ "solver_order": 2,
19
+ "solver_type": "midpoint",
20
  "steps_offset": 1,
21
+ "thresholding": false,
22
+ "timestep_spacing": "linspace",
23
+ "trained_betas": null,
24
+ "use_karras_sigmas": false,
25
+ "use_lu_lambdas": false,
26
+ "variance_type": null
27
  }
text_encoder/config.json CHANGED
@@ -20,6 +20,6 @@
20
  "pad_token_id": 1,
21
  "projection_dim": 512,
22
  "torch_dtype": "float32",
23
- "transformers_version": "4.25.0.dev0",
24
  "vocab_size": 49408
25
  }
 
20
  "pad_token_id": 1,
21
  "projection_dim": 512,
22
  "torch_dtype": "float32",
23
+ "transformers_version": "4.37.2",
24
  "vocab_size": 49408
25
  }
text_encoder/model.fp16.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:681c555376658c81dc273f2d737a2aeb23ddb6d1d8e5b3a7064636d359a22668
3
- size 680821096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97d075c1711b8bba3d68a662634737176429f2a0876916663d87ae959ec641b3
3
+ size 1168458360
text_encoder/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cce6febb0b6d876ee5eb24af35e27e764eb4f9b1d0b7c026c8c3333d4cfc916c
3
- size 1361597018
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97d075c1711b8bba3d68a662634737176429f2a0876916663d87ae959ec641b3
3
+ size 1168458360
tokenizer/tokenizer_config.json CHANGED
@@ -1,34 +1,38 @@
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
  "do_lower_case": true,
12
- "eos_token": {
13
- "__type": "AddedToken",
14
- "content": "<|endoftext|>",
15
- "lstrip": false,
16
- "normalized": true,
17
- "rstrip": false,
18
- "single_word": false
19
- },
20
  "errors": "replace",
21
  "model_max_length": 77,
22
- "name_or_path": "hf-models/stable-diffusion-v2-768x768/tokenizer",
23
- "pad_token": "<|endoftext|>",
24
- "special_tokens_map_file": "./special_tokens_map.json",
25
  "tokenizer_class": "CLIPTokenizer",
26
- "unk_token": {
27
- "__type": "AddedToken",
28
- "content": "<|endoftext|>",
29
- "lstrip": false,
30
- "normalized": true,
31
- "rstrip": false,
32
- "single_word": false
33
- }
34
  }
 
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
  }
unet/config.json CHANGED
@@ -1,13 +1,17 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.10.0.dev0",
4
  "act_fn": "silu",
 
 
 
5
  "attention_head_dim": [
6
  5,
7
  10,
8
  20,
9
  20
10
  ],
 
11
  "block_out_channels": [
12
  320,
13
  640,
@@ -15,7 +19,12 @@
15
  1280
16
  ],
17
  "center_input_sample": false,
 
 
 
 
18
  "cross_attention_dim": 1024,
 
19
  "down_block_types": [
20
  "CrossAttnDownBlock2D",
21
  "CrossAttnDownBlock2D",
@@ -23,24 +32,41 @@
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
  "norm_eps": 1e-05,
33
  "norm_num_groups": 32,
 
34
  "num_class_embeds": null,
35
  "only_cross_attention": false,
36
  "out_channels": 4,
37
- "sample_size": 96,
 
 
 
 
 
 
 
 
 
 
 
38
  "up_block_types": [
39
  "UpBlock2D",
40
  "CrossAttnUpBlock2D",
41
  "CrossAttnUpBlock2D",
42
  "CrossAttnUpBlock2D"
43
  ],
44
- "use_linear_projection": true,
45
- "upcast_attention": true
46
  }
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.27.0.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": [
9
  5,
10
  10,
11
  20,
12
  20
13
  ],
14
+ "attention_type": "default",
15
  "block_out_channels": [
16
  320,
17
  640,
 
19
  1280
20
  ],
21
  "center_input_sample": false,
22
+ "class_embed_type": null,
23
+ "class_embeddings_concat": false,
24
+ "conv_in_kernel": 3,
25
+ "conv_out_kernel": 3,
26
  "cross_attention_dim": 1024,
27
+ "cross_attention_norm": null,
28
  "down_block_types": [
29
  "CrossAttnDownBlock2D",
30
  "CrossAttnDownBlock2D",
 
32
  "DownBlock2D"
33
  ],
34
  "downsample_padding": 1,
35
+ "dropout": 0.0,
36
  "dual_cross_attention": false,
37
+ "encoder_hid_dim": null,
38
+ "encoder_hid_dim_type": null,
39
  "flip_sin_to_cos": true,
40
  "freq_shift": 0,
41
  "in_channels": 4,
42
  "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
  "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
  "norm_eps": 1e-05,
47
  "norm_num_groups": 32,
48
+ "num_attention_heads": null,
49
  "num_class_embeds": null,
50
  "only_cross_attention": false,
51
  "out_channels": 4,
52
+ "projection_class_embeddings_input_dim": null,
53
+ "resnet_out_scale_factor": 1.0,
54
+ "resnet_skip_time_act": false,
55
+ "resnet_time_scale_shift": "default",
56
+ "reverse_transformer_layers_per_block": null,
57
+ "sample_size": 64,
58
+ "time_cond_proj_dim": null,
59
+ "time_embedding_act_fn": null,
60
+ "time_embedding_dim": null,
61
+ "time_embedding_type": "positional",
62
+ "timestep_post_act": null,
63
+ "transformer_layers_per_block": 1,
64
  "up_block_types": [
65
  "UpBlock2D",
66
  "CrossAttnUpBlock2D",
67
  "CrossAttnUpBlock2D",
68
  "CrossAttnUpBlock2D"
69
  ],
70
+ "upcast_attention": null,
71
+ "use_linear_projection": true
72
  }
unet/diffusion_pytorch_model.fp16.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a3a4d7978884c5e4ef00b62641b1b544b257be2f6715d984188610ad6475ad2
3
- size 1731904736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96ebf655f21d1d25caef2b054072e550fd2255cf297ab41ffe89faf8566fb090
3
+ size 3463726504
unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1238522277c48923ff2751e238f2742c562e45643f3d50cc93d163cb30638b0c
3
- size 3463726498
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96ebf655f21d1d25caef2b054072e550fd2255cf297ab41ffe89faf8566fb090
3
+ size 3463726504
vae/config.json CHANGED
@@ -1,7 +1,6 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.8.0",
4
- "_name_or_path": "hf-models/stable-diffusion-v2-768x768/vae",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
@@ -15,12 +14,14 @@
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": 768,
 
24
  "up_block_types": [
25
  "UpDecoderBlock2D",
26
  "UpDecoderBlock2D",
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.27.0.dev0",
 
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
 
14
  "DownEncoderBlock2D",
15
  "DownEncoderBlock2D"
16
  ],
17
+ "force_upcast": true,
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": 512,
24
+ "scaling_factor": 0.18215,
25
  "up_block_types": [
26
  "UpDecoderBlock2D",
27
  "UpDecoderBlock2D",
vae/diffusion_pytorch_model.fp16.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
3
- size 167335342
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aa1f43011b553a4cba7f37456465cdbd48aab7b54b9348b890e8058ea7683ec
3
+ size 334643268
vae/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1d993488569e928462932c8c38a0760b874d166399b14414135bd9c42df5815
3
- size 334643276
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aa1f43011b553a4cba7f37456465cdbd48aab7b54b9348b890e8058ea7683ec
3
+ size 334643268