bloc97/CrossAttentionControl

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1337 stars · 83 forks observed · 2026-08-28

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

An unofficial Jupyter Notebook implementation of the 'Prompt-to-Prompt Image Editing with Cross Attention Control' paper adapted for Stable Diffusion. It enables fine-grained prompt-based image editing by modifying internal attention maps during inference, without masks or model fine-tuning.

Use cases

• edit stable diffusion images by changing prompt words without masks
• swap objects or attributes in AI-generated images
• perform image inversion to edit existing photos with stable diffusion
• control diffusion model output via cross attention maps
• reproduce prompt-to-prompt paper results on stable diffusion

When to choose

• you want mask-free prompt-based editing of Stable Diffusion images
• you want to edit existing images via DDIM inversion with cross attention control
• you prefer a notebook-based research implementation you can modify

When to avoid

• you need a maintained library compatible with recent diffusers versions
• you need a production-ready tool with a stable API
• you want plug-and-play image editing without running notebooks

Facets

library · maturity maintenance

image-processing machine-learning deep-learning image-processing artificial-intelligence deep-learning python stable-diffusion diffusion-models cross-attention prompt-to-prompt image-editing image-inversion jupyter-notebook diffusers gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="bloc97/CrossAttentionControl")