openai/consistencydecoder

Health v2 · maintenance only

Flags: no_releases archived

Adoption not part of the score

2212 stars · 81 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python library from OpenAI implementing a consistency-distilled diffusion VAE decoder that improves image decoding quality for Stable Diffusion VAE latents. It integrates with Hugging Face diffusers and PyTorch to replace the standard GAN decoder with higher-fidelity decoding.

Use cases

• decode stable diffusion latents with better image quality
• replace the GAN decoder in a stable diffusion VAE pipeline
• improve fidelity of generated images from stable diffusion
• run consistency models for image decoding
• integrate an improved VAE decoder into diffusers workflows

When to choose

• you use Stable Diffusion and want higher-quality decoded images from latents
• your pipeline already uses PyTorch and Hugging Face diffusers
• you have a CUDA GPU with memory for the ~2.5 GB model

When to avoid

• you need CPU-only inference or very low memory environments
• you use a different image generation stack without stable diffusion VAE latents
• you need actively maintained software with recent updates

Facets

library · maturity maintenance

image-processing machine-learning deep-learning image-processing machine-learning artificial-intelligence python stable-diffusion vae-decoder consistency-models diffusers image-generation gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="openai/consistencydecoder")