cloneofsimo/paint-with-words-sd

Implementation of Paint-with-words with Stable Diffusion : method from eDiff-I that let you generate image from text-labeled segmentation map.

42
/ 100
Emerging

Modifies Stable Diffusion's cross-attention mechanism to spatially condition generation via per-region text weights derived from segmentation maps, enabling precise object placement and composition control. Supports configurable attention weight scaling functions, regional random seeding for independent object synthesis, and inpainting workflows. Integrates with Hugging Face Diffusers and accepts community-standard checkpoint formats through conversion utilities.

645 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

645

Forks

49

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/cloneofsimo/paint-with-words-sd"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.