muzishen/IMAGHarmony
🧩 IMAGHarmony 🧩: Controllable image editing with consistent object quantity and layout. A structure-aware framework that ensures high fidelity and coherence in complex multi-object edits. It integrates harmony-aware attention and preference-guided noise selection to enable precise, stable, and semantically aligned generation.
This tool helps graphic designers, marketers, and content creators precisely edit images with multiple objects, ensuring consistent quantity and layout. You provide an existing image and your editing instructions, and it produces a new image where objects are added, removed, or rearranged exactly as specified, maintaining a natural and coherent scene. This is ideal for anyone needing fine-grained control over complex image compositions.
607 stars.
Use this if you need to reliably change the number, type, or arrangement of objects within an image without distorting the scene or individual elements.
Not ideal if you only need simple image adjustments like cropping, color correction, or single-object modifications.
Stars
607
Forks
45
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/muzishen/IMAGHarmony"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
bytedance/InfiniteYou
🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
River-Zhang/ICEdit
[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image...
AMAP-ML/FE2E
[CVPR 2026] Beyond Generation: Advancing Image Editing Priors for Depth and Normal Estimation
TencentARC/BrushNet
[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting...
ermongroup/SDEdit
PyTorch implementation for SDEdit: Image Synthesis and Editing with Stochastic Differential Equations