Duplicate from openai/consistency-decoder

Co-authored-by: Patrick von Platen <patrickvonplaten@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,37 @@
+---
+library_name: diffusers
+tags:
+- stable-diffusion
+license: mit
+---
+
+## Consistency Decoder
+
+This is a decoder that can be used to improve decoding for Stable Diffusion VAEs. To know more, refer to the [DALL-E 3 technical report](https://cdn.openai.com/papers/dall-e-3.pdf). 
+
+To original code repository can be found [here](https://github.com/openai/consistencydecoder). 
+
+## Usage in 🧨 diffusers
+
+```python
+import torch
+from diffusers import DiffusionPipeline, ConsistencyDecoderVAE
+
+vae = ConsistencyDecoderVAE.from_pretrained("openai/consistency-decoder", torch_dtype=pipe.torch_dtype)
+pipe = StableDiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5", vae=vae, torch_dtype=torch.float16
+).to("cuda")
+
+pipe("horse", generator=torch.manual_seed(0)).images
+```
+
+## Results
+
+_(Taken from the original [code repository](https://github.com/openai/consistencydecoder))_
+
+## Examples
+ Original Image | GAN Decoder | Consistency Decoder |
+:---:|:---:|:---:|
+![Original Image](https://github.com/openai/consistencydecoder/blob/main/assets/gt1.png?raw=true) | ![GAN Image](https://github.com/openai/consistencydecoder/blob/main/assets/gan1.png?raw=true) | ![VAE Image](https://github.com/openai/consistencydecoder/blob/main/assets/con1.png?raw=true) |
+![Original Image](https://github.com/openai/consistencydecoder/blob/main/assets/gt2.png?raw=true) | ![GAN Image](https://github.com/openai/consistencydecoder/blob/main/assets/gan2.png?raw=true) | ![VAE Image](https://github.com/openai/consistencydecoder/blob/main/assets/con2.png?raw=true) |
+![Original Image](https://github.com/openai/consistencydecoder/blob/main/assets/gt3.png?raw=true) | ![GAN Image](https://github.com/openai/consistencydecoder/blob/main/assets/gan3.png?raw=true) | ![VAE Image](https://github.com/openai/consistencydecoder/blob/main/assets/con3.png?raw=true) |

config.json

@@ -0,0 +1,53 @@
+{
+  "_class_name": "ConsistencyDecoderVAE",
+  "_diffusers_version": "0.23.0.dev0",
+  "_name_or_path": "openai/consistency-decoder",
+  "decoder_add_attention": false,
+  "decoder_block_out_channels": [
+    320,
+    640,
+    1024,
+    1024
+  ],
+  "decoder_down_block_types": [
+    "ResnetDownsampleBlock2D",
+    "ResnetDownsampleBlock2D",
+    "ResnetDownsampleBlock2D",
+    "ResnetDownsampleBlock2D"
+  ],
+  "decoder_downsample_padding": 1,
+  "decoder_in_channels": 7,
+  "decoder_layers_per_block": 3,
+  "decoder_norm_eps": 1e-05,
+  "decoder_norm_num_groups": 32,
+  "decoder_num_train_timesteps": 1024,
+  "decoder_out_channels": 6,
+  "decoder_resnet_time_scale_shift": "scale_shift",
+  "decoder_time_embedding_type": "learned",
+  "decoder_up_block_types": [
+    "ResnetUpsampleBlock2D",
+    "ResnetUpsampleBlock2D",
+    "ResnetUpsampleBlock2D",
+    "ResnetUpsampleBlock2D"
+  ],
+  "encoder_act_fn": "silu",
+  "encoder_block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "encoder_double_z": true,
+  "encoder_down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "encoder_in_channels": 3,
+  "encoder_layers_per_block": 2,
+  "encoder_norm_num_groups": 32,
+  "encoder_out_channels": 4,
+  "latent_channels": 4,
+  "scaling_factor": 0.18215
+}

diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6386a06f741c7dfaaa4709b6db39aca345a406d8413dc2c4dbd48a0dce1cfb
+size 1310944884

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6386a06f741c7dfaaa4709b6db39aca345a406d8413dc2c4dbd48a0dce1cfb
+size 1310944884