omriav/blended-latent-diffusion

Official implementation for "Blended Latent Diffusion" [SIGGRAPH 2023]

40
/ 100
Emerging

This helps graphic designers, marketers, and content creators quickly edit specific parts of an image using text descriptions. You provide an existing image, highlight the area to change with a mask, and describe the desired edit with text. The project then generates new image options for that masked region, seamlessly blended into the original picture.

629 stars. No commits in the last 6 months.

Use this if you need to make fast, localized, text-driven edits to images, such as changing backgrounds, altering objects, or adding new elements, without complex manual photo editing.

Not ideal if you need to generate entirely new images from scratch or perform very subtle, pixel-level retouches that require extreme precision.

graphic design image editing digital art content creation marketing visuals
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

629

Forks

37

Language

Jupyter Notebook

License

MIT

Last pushed

Jun 04, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/omriav/blended-latent-diffusion"

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