init

README.md

@@ -1,3 +1,62 @@
 ---
-license: apache-2.0
+license: openrail++
+tags:
+- text-to-image
+- stable-diffusion
+library_name: diffusers
+inference: false
 ---
+
+# SDXS-512-0.9
+
+SDXS is a model that can generate high-resolution images in real-time based on prompt texts, trained using score distillation and feature matching. For more information, please refer to our research paper: SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions. We open-source the model as part of the research.
+
+SDXS-512-0.9 is a **old version** of SDXS-512. For some reasons, we are only releasing this version for the time being, and will gradually release other versions.
+
+Model Information:
+- Teacher DM: [SD Turbo](https://huggingface.co/stabilityai/sd-turbo)
+- Offline DM: [SD v2.1 base](https://huggingface.co/stabilityai/stable-diffusion-2-1-base)
+- VAE: [TAESD](https://huggingface.co/madebyollin/taesd)
+
+Note that TAESD may produce low-quality images when weight_type is float16. Our image decoder is not compatible with the current version of diffusers, so it will not be provided now.
+
+## Diffusers Usage
+
+![](output.png)
+
+```python
+import torch
+from diffusers import StableDiffusionPipeline, AutoencoderKL
+
+repo = "IDKiro/sdxs-512-0.9"
+seed = 42
+weight_type = torch.float32     # or float16
+
+# Load model.
+pipe = StableDiffusionPipeline.from_pretrained(repo, torch_dtype=weight_type)
+# pipe.vae = AutoencoderKL.from_pretrained("IDKiro/sdxs-512-0.9/vae_large")     # use original VAE
+pipe.to("cuda")
+
+prompt = "portrait photo of a girl, photograph, highly detailed face, depth of field, moody light, golden hour"
+
+# Ensure using the same inference steps as the loaded model and CFG set to 0.
+image = pipe(
+    prompt, 
+    num_inference_steps=1, 
+    guidance_scale=0,
+    generator=torch.Generator(device="cuda").manual_seed(seed)
+).images[0]
+
+image.save("output.png")
+```
+
+## Cite Our Work
+
+```
+@article{park2021nerfies,
+  author    = {Yuda Song, Zehao Sun, Xuanwu Yin},
+  title     = {SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions},
+  journal   = {arxiv},
+  year      = {2024},
+}
+```

demo.py

@@ -0,0 +1,23 @@
+import torch
+from diffusers import StableDiffusionPipeline, AutoencoderKL
+
+repo = "IDKiro/sdxs-512-0.9"
+seed = 42
+weight_type = torch.float32
+
+# Load model.
+pipe = StableDiffusionPipeline.from_pretrained(repo, torch_dtype=weight_type)
+# pipe.vae = AutoencoderKL.from_pretrained("IDKiro/sdxs-512-0.9/vae_large")     # use original VAE
+pipe.to("cuda")
+
+prompt = "portrait photo of a girl, photograph, highly detailed face, depth of field, moody light, golden hour"
+
+# Ensure using the same inference steps as the loaded model and CFG set to 0.
+image = pipe(
+    prompt, 
+    num_inference_steps=1, 
+    guidance_scale=0,
+    generator=torch.Generator(device="cuda").manual_seed(seed)
+).images[0]
+
+image.save("output.png")

feature_extractor/preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.10.0.dev0",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "requires_safety_checker": false,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderTiny"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.19.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "interpolation_type": "linear",
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "trailing",
+  "trained_betas": null,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "stabilityai/stable-diffusion-2",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.0.dev0",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cce6febb0b6d876ee5eb24af35e27e764eb4f9b1d0b7c026c8c3333d4cfc916c
+size 1361597018

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3e254d7b61353497ea0be2c4013df4ea8f739ee88cffa0ba58cd085459ed565
+size 1361671895

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "name_or_path": "stabilityai/stable-diffusion-2",
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -0,0 +1,73 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.23.1",
+  "_name_or_path": "/local/scratch5/songyuda/pretrained/sd-turbo/",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": [
+    8,
+    8,
+    8
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 1024,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 1,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": null,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": [
+    true,
+    false,
+    false
+  ],
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2afb7dbea11b64d0bfbc4d1a45854aa65408b8a74a732438225d3f2ec85c71c
+size 1312752864

vae/config.json

@@ -0,0 +1,44 @@
+{
+  "_class_name": "AutoencoderTiny",
+  "_diffusers_version": "0.20.0.dev0",
+  "act_fn": "relu",
+  "block_out_channels": [
+    64,
+    64,
+    64,
+    64
+  ],
+  "decoder_block_out_channels": [
+    64,
+    64,
+    64,
+    64
+  ],
+  "encoder_block_out_channels": [
+    64,
+    64,
+    64,
+    64
+  ],
+  "force_upcast": false,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latent_magnitude": 3,
+  "latent_shift": 0.5,
+  "num_decoder_blocks": [
+    3,
+    3,
+    3,
+    1
+  ],
+  "num_encoder_blocks": [
+    1,
+    3,
+    3,
+    3
+  ],
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 1.0,
+  "upsampling_scaling_factor": 2
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7956d561b1efbd861ad9b03fd8f01510f9e87eddc07bdfd20837009433f6ee5
+size 9793292

vae_large/config.json

@@ -0,0 +1,29 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.10.0.dev0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 768,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae_large/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d993488569e928462932c8c38a0760b874d166399b14414135bd9c42df5815
+size 334643276