patrickvonplaten commited on
Commit
3a98214
1 Parent(s): 97a4ac5

Add diffusers weights (#4)

Browse files

- add diffusers weighst (51e1b905f0d644efa6685a6912a45c72962be30b)
- correct scheduler (647e47abb87343a8a42170b6f73255d72443ef70)
- correct scheduler (62f39588cb2d6e3fe28ad8662d16236229eb87be)
- add diffusers example (8594b431d382cc5e0d8ba577e6470e71851250a4)

README.md CHANGED
@@ -60,6 +60,49 @@ The model is intended for research purposes only. Possible research areas and ta
60
 
61
  Excluded uses are described below.
62
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  ### Out-of-Scope Use
64
 
65
  The model was not trained to be factual or true representations of people or events,
 
60
 
61
  Excluded uses are described below.
62
 
63
+ ### Diffusers
64
+
65
+ ```
66
+ pip install diffusers transformers accelerate --upgrade
67
+ ```
68
+
69
+ - **Text-to-image**:
70
+
71
+ SDXL-Turbo does not make use of `guidance_scale` or `negative_prompt`, we disable it with `guidance_scale=0.0`.
72
+ Preferably, the model generates images of size 512x512 but higher image sizes work as well.
73
+ A **single step** is enough to generate high quality images.
74
+
75
+ ```py
76
+ from diffusers import AutoPipelineForText2Image
77
+ import torch
78
+
79
+ pipe = AutoPipelineForText2Image.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16")
80
+ pipe.to("cuda")
81
+
82
+ prompt = "A cinematic shot of a baby racoon wearing an intricate italian priest robe."
83
+
84
+ image = pipe(prompt=prompt, num_inference_steps=1, guidance_scale=0.0).images[0]
85
+ ```
86
+
87
+ - **Image-to-image**:
88
+
89
+ When using SDXL-Turbo for image-to-image generation, make sure that `num_inference_steps` * `strength` is larger or equal
90
+ to 1. The image-to-image pipeline will run for `int(num_inference_steps * strength)` steps, *e.g.* 0.5 * 2.0 = 1 step in our example
91
+ below.
92
+
93
+ ```py
94
+ from diffusers import AutoPipelineForImage2Image
95
+ from diffusers.utils import load_image
96
+
97
+ pipe = AutoPipelineForImage2Image.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16")
98
+
99
+ init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png").resize((512, 512))
100
+
101
+ prompt = "cat wizard, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney, 8k"
102
+
103
+ image = pipe(prompt, image=init_image, num_inference_steps=2, strength=0.5, guidance_scale=0.0).images[0]
104
+ ```
105
+
106
  ### Out-of-Scope Use
107
 
108
  The model was not trained to be factual or true representations of people or events,
model_index.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionXLPipeline",
3
+ "_diffusers_version": "0.24.0.dev0",
4
+ "feature_extractor": [
5
+ null,
6
+ null
7
+ ],
8
+ "force_zeros_for_empty_prompt": true,
9
+ "image_encoder": [
10
+ null,
11
+ null
12
+ ],
13
+ "scheduler": [
14
+ "diffusers",
15
+ "EulerAncestralDiscreteScheduler"
16
+ ],
17
+ "text_encoder": [
18
+ "transformers",
19
+ "CLIPTextModel"
20
+ ],
21
+ "text_encoder_2": [
22
+ "transformers",
23
+ "CLIPTextModelWithProjection"
24
+ ],
25
+ "tokenizer": [
26
+ "transformers",
27
+ "CLIPTokenizer"
28
+ ],
29
+ "tokenizer_2": [
30
+ "transformers",
31
+ "CLIPTokenizer"
32
+ ],
33
+ "unet": [
34
+ "diffusers",
35
+ "UNet2DConditionModel"
36
+ ],
37
+ "vae": [
38
+ "diffusers",
39
+ "AutoencoderKL"
40
+ ]
41
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "EulerAncestralDiscreteScheduler",
3
+ "_diffusers_version": "0.24.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "interpolation_type": "linear",
9
+ "num_train_timesteps": 1000,
10
+ "prediction_type": "epsilon",
11
+ "sample_max_value": 1.0,
12
+ "set_alpha_to_one": false,
13
+ "skip_prk_steps": true,
14
+ "steps_offset": 1,
15
+ "timestep_spacing": "trailing",
16
+ "trained_betas": null
17
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "4.36.0.dev0",
23
+ "vocab_size": 49408
24
+ }
text_encoder/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
3
+ size 246144152
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:778d02eb9e707c3fbaae0b67b79ea0d1399b52e624fb634f2f19375ae7c047c3
3
+ size 492265168
text_encoder_2/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CLIPTextModelWithProjection"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 0,
7
+ "dropout": 0.0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_size": 1280,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5120,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 77,
16
+ "model_type": "clip_text_model",
17
+ "num_attention_heads": 20,
18
+ "num_hidden_layers": 32,
19
+ "pad_token_id": 1,
20
+ "projection_dim": 1280,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.36.0.dev0",
23
+ "vocab_size": 49408
24
+ }
text_encoder_2/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
3
+ size 1389382176
text_encoder_2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa5b2e6f4c2efc2d82e4b8312faec1a5540eabfc6415126c9a05c8436a530ef4
3
+ size 2778702264
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
The diff for this file is too large to render. See raw diff
 
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 ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.24.0.dev0",
4
+ "act_fn": "silu",
5
+ "addition_embed_type": "text_time",
6
+ "addition_embed_type_num_heads": 64,
7
+ "addition_time_embed_dim": 256,
8
+ "attention_head_dim": [
9
+ 5,
10
+ 10,
11
+ 20
12
+ ],
13
+ "attention_type": "default",
14
+ "block_out_channels": [
15
+ 320,
16
+ 640,
17
+ 1280
18
+ ],
19
+ "center_input_sample": false,
20
+ "class_embed_type": null,
21
+ "class_embeddings_concat": false,
22
+ "conv_in_kernel": 3,
23
+ "conv_out_kernel": 3,
24
+ "cross_attention_dim": 2048,
25
+ "cross_attention_norm": null,
26
+ "down_block_types": [
27
+ "DownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "CrossAttnDownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "dropout": 0.0,
33
+ "dual_cross_attention": false,
34
+ "encoder_hid_dim": null,
35
+ "encoder_hid_dim_type": null,
36
+ "flip_sin_to_cos": true,
37
+ "freq_shift": 0,
38
+ "in_channels": 4,
39
+ "layers_per_block": 2,
40
+ "mid_block_only_cross_attention": null,
41
+ "mid_block_scale_factor": 1,
42
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
43
+ "norm_eps": 1e-05,
44
+ "norm_num_groups": 32,
45
+ "num_attention_heads": null,
46
+ "num_class_embeds": null,
47
+ "only_cross_attention": false,
48
+ "out_channels": 4,
49
+ "projection_class_embeddings_input_dim": 2816,
50
+ "resnet_out_scale_factor": 1.0,
51
+ "resnet_skip_time_act": false,
52
+ "resnet_time_scale_shift": "default",
53
+ "reverse_transformer_layers_per_block": null,
54
+ "sample_size": 64,
55
+ "time_cond_proj_dim": null,
56
+ "time_embedding_act_fn": null,
57
+ "time_embedding_dim": null,
58
+ "time_embedding_type": "positional",
59
+ "timestep_post_act": null,
60
+ "transformer_layers_per_block": [
61
+ 1,
62
+ 2,
63
+ 10
64
+ ],
65
+ "up_block_types": [
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "UpBlock2D"
69
+ ],
70
+ "upcast_attention": null,
71
+ "use_linear_projection": true
72
+ }
unet/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48fa46161a745f48d4054df3fe13804ee255486bca893403b60373c188fd1bdb
3
+ size 5135149760
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1968fc61aa8449ab3d3f9b9a05bce88c611760c01e0c4a7a3785911b546fe582
3
+ size 10270077736
vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.24.0.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
+ "layers_per_block": 2,
21
+ "norm_num_groups": 32,
22
+ "out_channels": 3,
23
+ "sample_size": 1024,
24
+ "scaling_factor": 0.13025,
25
+ "up_block_types": [
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D"
30
+ ]
31
+ }
vae/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02ee4bd18e5d16e7fe5fc5b85b4aefa2cba6db28897f674226c9d6ddd2f34f06
3
+ size 167335342
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:716971093e3428c9156906fcbcc5500abf005317c5f4d3a5bb3fa28c45e1e071
3
+ size 334643268