PeterL1n commited on
Commit
5866997
1 Parent(s): 6b2964b

Publish model

Browse files
README.md CHANGED
@@ -1,3 +1,55 @@
1
  ---
2
- license: openrail
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: openrail++
3
+ tags:
4
+ - stable-diffusion
5
+ - text-to-image
6
  ---
7
+
8
+ # SD v2.1-base with Self-Perceptual Objective
9
+
10
+ This is the official model in [Diffusion Model with Perceptual Loss](https://arxiv.org/abs/2401.00110) paper.
11
+
12
+ This model is trained using the self-perceptual objective. It no longer needs classifier-free guidance to produce sensible images.
13
+
14
+ This model is trained using zero terminal SNR schedule following [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://arxiv.org/abs/2305.08891) paper on LAION aesthetic 6+ data.
15
+
16
+ This model is finetuned from [stabilityai/stable-diffusion-2-1-base](https://huggingface.co/stabilityai/stable-diffusion-2-1-base).
17
+
18
+ This model is meant for research demonstration, not for production use.
19
+
20
+ ## Usage
21
+
22
+ ```python
23
+ from diffusers import StableDiffusionPipeline
24
+ prompt = "A young girl smiling"
25
+ pipe = StableDiffusionPipeline.from_pretrained("ByteDance/sd2.1-base-zsnr-laionaes6-perceptual").to("cuda")
26
+ pipe(prompt, guidance_scale=0).images[0].save("out.jpg") # No need for CFG!
27
+ ```
28
+
29
+ ## Related Models
30
+
31
+ * [bytedance/sd2.1-base-zsnr-laionaes5](https://huggingface.co/ByteDance/sd2.1-base-zsnr-laionaes5)
32
+ * [bytedance/sd2.1-base-zsnr-laionaes6](https://huggingface.co/ByteDance/sd2.1-base-zsnr-laionaes6)
33
+ * [bytedance/sd2.1-base-zsnr-laionaes6-perceptual](https://huggingface.co/ByteDance/sd2.1-base-zsnr-laionaes6-perceptual)
34
+
35
+
36
+ ## Cite as
37
+ ```
38
+ @misc{lin2024diffusion,
39
+ title={Diffusion Model with Perceptual Loss},
40
+ author={Shanchuan Lin and Xiao Yang},
41
+ year={2024},
42
+ eprint={2401.00110},
43
+ archivePrefix={arXiv},
44
+ primaryClass={cs.CV}
45
+ }
46
+
47
+ @misc{lin2023common,
48
+ title={Common Diffusion Noise Schedules and Sample Steps are Flawed},
49
+ author={Shanchuan Lin and Bingchen Liu and Jiashi Li and Xiao Yang},
50
+ year={2023},
51
+ eprint={2305.08891},
52
+ archivePrefix={arXiv},
53
+ primaryClass={cs.CV}
54
+ }
55
+ ```
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": 224,
3
+ "do_center_crop": true,
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "do_resize": true,
7
+ "feature_extractor_type": "CLIPFeatureExtractor",
8
+ "image_mean": [
9
+ 0.48145466,
10
+ 0.4578275,
11
+ 0.40821073
12
+ ],
13
+ "image_std": [
14
+ 0.26862954,
15
+ 0.26130258,
16
+ 0.27577711
17
+ ],
18
+ "resample": 3,
19
+ "size": 224
20
+ }
model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.23.1",
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",
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
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.23.1",
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": true,
11
+ "steps_offset": 1,
12
+ "trained_betas": null,
13
+ "timestep_spacing": "trailing",
14
+ "rescale_betas_zero_snr": true
15
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stabilityai/stable-diffusion-2",
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": "gelu",
11
+ "hidden_size": 1024,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 23,
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
+ }
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e254d7b61353497ea0be2c4013df4ea8f739ee88cffa0ba58cd085459ed565
3
+ size 1361671895
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": "!",
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "stabilityai/stable-diffusion-2",
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
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "cross_attention_dim": 1024,
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
+ "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": 64,
38
+ "up_block_types": [
39
+ "UpBlock2D",
40
+ "CrossAttnUpBlock2D",
41
+ "CrossAttnUpBlock2D",
42
+ "CrossAttnUpBlock2D"
43
+ ],
44
+ "use_linear_projection": true
45
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d51403065b0bcdf87205776a0acb115781e5a6719f93f1b7440d264b51f85b43
3
+ size 3463925434
vae/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.10.0.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
+ "in_channels": 3,
18
+ "latent_channels": 4,
19
+ "layers_per_block": 2,
20
+ "norm_num_groups": 32,
21
+ "out_channels": 3,
22
+ "sample_size": 768,
23
+ "up_block_types": [
24
+ "UpDecoderBlock2D",
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D"
28
+ ]
29
+ }
vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b4889b6b1d4ce7ae320a02dedaeff1780ad77d415ea0d744b476155c6377ddc
3
+ size 334707217