muzishen / IMAGHarmonyLinks
π§© IMAGHarmony π§©: Controllable image editing with consistent object quantity and layout. A structure-aware framework that ensures high fidelity and coherence in complex multi-object edits. IMAGHarmony integrates harmony-aware attention and preference-guided noise selection to enable precise, stable, and semantically aligned generation.
β18Updated 2 weeks ago
Alternatives and similar repositories for IMAGHarmony
Users that are interested in IMAGHarmony are comparing it to the libraries listed below
Sorting:
- β26Updated 3 months ago
- UniCombine: Unified Multi-Conditional Combination with Diffusion Transformerβ91Updated last week
- [CVPR2025] Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editingβ14Updated this week
- β33Updated 7 months ago
- Official code for CustAny: Customizing Anything from A Single Example. Accepted by CVPR2025 (Oral)β46Updated 2 months ago
- Official implementation of "IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation".β55Updated 9 months ago
- Official code of "Edit Transfer: Learning Image Editing via Vision In-Context Relations"β79Updated 3 weeks ago
- Video Diffusion Transformers are In-Context Learnersβ23Updated 5 months ago
- Official PyTorch Implementation of "Giving a Hand to Diffusion Models: a Two-Stage Approach to Improving Conditional Human Image Generatiβ¦β26Updated last year
- β40Updated 5 months ago
- β26Updated last year
- This repo contains the code for PreciseControl project [ECCV'24]β63Updated 8 months ago
- Conceptrol: Concept Control of Zero-shot Personalized Image Generationβ39Updated 3 months ago
- [CVPR 2025] PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generationβ36Updated 4 months ago
- Implementation code of the paper MIGE: A Unified Framework for Multimodal Instruction-Based Image Generation and Editingβ64Updated 2 weeks ago
- β83Updated 3 weeks ago
- Eye-for-an-eye: Appearance Transfer with Semantic Correspondence in Diffusion Modelsβ28Updated 9 months ago
- Maximize the Resolution Potential of Pre-trained Rectified Flow Transformersβ52Updated 8 months ago
- [ECCV2024] Source Prompt Disentangled Inversion for Boosting Image Editability with Diffusion Modelsβ42Updated 11 months ago
- Official implementation of ImprovingText-guided ObjectInpainting with SemanticPre-inpainting in ECCV 2024β55Updated 6 months ago
- EEditβ‘: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editingβ29Updated 3 months ago
- β50Updated 6 months ago
- β44Updated 8 months ago
- OneIG-Bench is a meticulously designed comprehensive benchmark framework for fine-grained evaluation of T2I models across multiple dimensβ¦β35Updated 2 weeks ago
- β19Updated 7 months ago
- [Arxiv'25] BlobCtrl: A Unified and Flexible Framework for Element-level Image Generation and Editingβ90Updated 3 months ago
- β33Updated 3 months ago
- Official Implement of the work "Coherent and Multi-modality Image Inpainting via Latent Space Optimization"β53Updated 2 months ago
- Official repository of IDEA-Benchβ35Updated 5 months ago
- [Arxiv 2024] Edicho: Consistent Image Editing in the Wildβ117Updated 5 months ago