HolmesShuan / FireFlow-Fast-Inversion-of-Rectified-Flow-for-Image-Semantic-EditingLinks
[ICML2025] An 8-step inversion and 8-step editing process works effectively with the FLUX-dev model. (3x speedup with results that are comparable or even superior to baseline methods)
☆268Updated last month
Alternatives and similar repositories for FireFlow-Fast-Inversion-of-Rectified-Flow-for-Image-Semantic-Editing
Users that are interested in FireFlow-Fast-Inversion-of-Rectified-Flow-for-Image-Semantic-Editing are comparing it to the libraries listed below
Sorting:
- IP Adapter Instruct☆204Updated 9 months ago
- Official implementation of "Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance" (NeurIPS 2024)☆290Updated 3 weeks ago
- Personalize Anything for Free with Diffusion Transformer☆326Updated 2 months ago
- Rectified Flow Inversion (RF-Inversion) - ICLR 2025☆412Updated 2 months ago
- Official code for VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Control☆185Updated 5 months ago
- ☆180Updated 3 weeks ago
- Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"☆626Updated 4 months ago
- Official implementation for KV-Edit: Training-Free Image Editing for Precise Background Preservation☆306Updated last week
- [ICLR 2025] Codebase for "CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation"☆232Updated 4 months ago
- ☆408Updated 6 months ago
- ☆255Updated 6 months ago
- CSGO: Content-Style Composition in Text-to-Image Generation 🔥☆341Updated 8 months ago
- OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting☆220Updated last month
- ☆434Updated last year
- HunyuanVideo Keyframe Control Lora is an adapter for HunyuanVideo T2V model for keyframe-based video generation☆139Updated 2 months ago
- Implicit Style-Content Separation using B-LoRA☆373Updated 6 months ago
- Community trainer for Lightricks' LTX Video model 🎬 ⚡️☆180Updated last week
- VisualCloze: A universal image generation framework that can support a wide range of in-domain tasks and generalize to unseen ones. (🔥 �…☆227Updated 2 weeks ago
- ☆160Updated last month
- Training-free Regional Prompting for Diffusion Transformers 🔥☆647Updated 6 months ago
- [ICLR 2025] Official implementation of MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance☆272Updated last month
- ☆403Updated this week
- LayerAnimate: Layer-specific Control for Animation☆156Updated this week
- ☆236Updated 2 months ago
- The official code implementation of the paper "OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data."☆119Updated this week
- implementation of the IPAdapter models for HF Diffusers☆172Updated last year
- CatV2TON is a lightweight DiT-based visual virtual try-on model, capable of supporting try-on for both images and videos.☆140Updated 3 months ago
- UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization☆252Updated last month
- [CVPR 2025] Consistent and Controllable Image Animation with Motion Diffusion Models☆272Updated 2 weeks ago
- ☆78Updated last month