hohonu-vicml/DirectedDiffusion

Directed Diffusion: Direct Control of Object Placement through Attention Guidance (AAAI2024)

25
/ 100
Experimental

This tool helps creators, marketers, or storytellers accurately place multiple objects or characters within AI-generated images. Instead of hoping a text prompt generates your desired scene, you can specify exactly where elements like people, products, or props should appear. This gives you precise visual control, making it easier to create consistent and narrative-driven imagery for projects like storyboards or marketing campaigns.

No commits in the last 6 months.

Use this if you need to generate images from text descriptions but find current AI models struggle with placing specific objects in precise locations or maintaining spatial relationships between elements.

Not ideal if your image generation needs are for single objects or abstract scenes where precise spatial control of multiple elements is not critical.

AI-art-direction visual-storytelling marketing-asset-creation content-design character-placement
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

81

Forks

5

Language

Python

License

Last pushed

Feb 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/hohonu-vicml/DirectedDiffusion"

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