consistency-decoder
OpenAI's consistency model decoder for Stable Diffusion that converts latent representations into high-quality images.
Model Card
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.
To original code repository can be found here.
Usage in 𧨠diffusers
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)
Examples
| Original Image | GAN Decoder | Consistency Decoder |
|---|---|---|
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
Get the full context.
Sign up to read complete case studies, access detailed metrics, and unlock all use cases.
Get the full context.
Sign up to read complete case studies, access detailed metrics, and unlock all use cases.








