O

consistency-decoder

Otherby OpenAIΒ·Model page β†—

OpenAI's consistency model decoder for Stable Diffusion that converts latent representations into high-quality images.

Share:

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 🧨 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
Original Image GAN Image VAE Image
Original Image GAN Image VAE Image
Original Image GAN Image VAE Image
Author
O
OpenAI
Organization Β· βœ“
openai
Details
Downloads124
Likes53
AccessOpen Source
Licensemit
Librarydiffusers
CreatedNov 9, 2023
UpdatedNov 9, 2023
View on Hugging Face
Get the full context.

Sign up to read complete case studies, access detailed metrics, and unlock all use cases.

consistency-decoder β€” AI Model Details | Applied