donahowe/AutoStudio

AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation

33
/ 100
Emerging

Employs a training-free multi-agent LLM framework coordinating subject management, spatial layout generation, and refinement supervision alongside a Parallel-UNet diffusion model with dual cross-attention modules for consistent multi-subject image generation. Integrates Stable Diffusion (v1.5 and SDXL), IP-Adapter, Grounding-DINO, and EfficientSAM for dialogue-driven interactive generation across multiple turns while maintaining subject identity and spatial coherence.

449 stars. No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

449

Forks

30

Language

Jupyter Notebook

License

Last pushed

Apr 13, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/donahowe/AutoStudio"

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