google/break-a-scene
Official implementation for "Break-A-Scene: Extracting Multiple Concepts from a Single Image" [SIGGRAPH Asia 2023]
This tool helps graphic designers, digital artists, and marketers isolate and manipulate individual elements within a single image. You provide an image along with rough outlines (masks) for each concept you want to separate. The tool then learns to recognize these concepts, allowing you to generate new images where these elements are recombined, varied, or placed in different scenes using text prompts.
525 stars. No commits in the last 6 months.
Use this if you need to extract multiple distinct objects or subjects from a single image and re-use or re-imagine them in new creative contexts.
Not ideal if you're looking for an automated one-click solution for general object detection without providing segmentation masks, or if you only need basic image cropping.
Stars
525
Forks
26
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 14, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/google/break-a-scene"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
mit-han-lab/distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Tencent-Hunyuan/HunyuanPortrait
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced...
giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...