InstantIR: Blind Image Restoration with Instant Generative Reference π₯
β529Nov 14, 2024Updated last year
Alternatives and similar repositories for InstantIR
Users that are interested in InstantIR are comparing it to the libraries listed below
Sorting:
- You can InstantIR to upsacel image in ComfyUI οΌInstantIR,Blind Image Restoration with Instant Generative Referenceβ243Mar 12, 2025Updated 11 months ago
- β427Nov 4, 2024Updated last year
- [NeurIPS 2024] Generalizable Implicit Motion Modeling for Video Frame Interpolationβ381Jun 5, 2025Updated 9 months ago
- AuraSR: GAN-based Super-Resolution for real-worldβ513Nov 13, 2024Updated last year
- Training-free Regional Prompting for Diffusion Transformers π₯β694Nov 28, 2024Updated last year
- [ICLR 2025] Official implementation of Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restorationβ741Feb 5, 2025Updated last year
- OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340β4,311Dec 4, 2025Updated 3 months ago
- [ICCV 2025 Highlight] OminiControl: Minimal and Universal Control for Diffusion Transformerβ1,903Jul 3, 2025Updated 8 months ago
- Nodes for image juxtaposition for Flux in ComfyUIβ1,397Jan 9, 2025Updated last year
- [ICCV'25]DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusionβ1,328Oct 17, 2025Updated 4 months ago
- β479Oct 30, 2024Updated last year
- Rectified Flow Inversion (RF-Inversion) - ICLR 2025β470Mar 19, 2025Updated 11 months ago
- Official implementation of OneDiffusion paper (CVPR 2025)β665Dec 14, 2024Updated last year
- A port of muerrilla's sd-webui-Detail-Daemon as a node for ComfyUI, to adjust sigmas that control detail.β938Dec 21, 2025Updated 2 months ago
- [ECCV 2024] HiDiffusion: Increases the resolution and speed of your diffusion model by only adding a single line of code!β838Jan 7, 2026Updated 2 months ago
- Enhance-A-Video: Better Generated Video for Freeβ594Mar 17, 2025Updated 11 months ago
- Official repository of In-Context LoRA for Diffusion Transformersβ2,059Dec 20, 2024Updated last year
- [NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignmentβ3,520Jul 31, 2025Updated 7 months ago
- [CVPR 2025] MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3Dβ248Aug 22, 2025Updated 6 months ago
- [ECCV'24] Kalman-Inspired Feature Propagation for Video Face Super-Resolutionβ500May 14, 2025Updated 9 months ago
- ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignmentβ1,280Jul 17, 2024Updated last year
- Official implementation of "Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance" (NeurIPS 2024)β307Sep 12, 2025Updated 5 months ago
- Custom Conditioning Delta (ConDelta) nodes for ComfyUIβ208Sep 3, 2025Updated 6 months ago
- β572Nov 26, 2024Updated last year
- Official code for VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Controlβ191Dec 31, 2024Updated last year
- β81Mar 31, 2025Updated 11 months ago
- β2,612Aug 21, 2024Updated last year
- [ICLR 2025] Codebase for "CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation"β263Jan 12, 2026Updated last month
- β235Oct 11, 2024Updated last year
- Source code for the SIGGRAPH 2024 paper "X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention"β536Oct 14, 2025Updated 4 months ago
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Modelsβ3,703Feb 14, 2026Updated 3 weeks ago
- Illumination Drawing Tools for Text-to-Image Diffusion Modelsβ776May 4, 2025Updated 10 months ago
- Implementation of UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaksβ613Sep 27, 2024Updated last year
- β1,049May 14, 2025Updated 9 months ago
- [NeurIPS 2024] DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curationβ1,191Mar 21, 2025Updated 11 months ago
- The official HelloMeme GitHub siteβ627Jun 27, 2025Updated 8 months ago
- Official repo for CFG-Zero*β706May 2, 2025Updated 10 months ago
- [ICCV 2025] STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolutionβ1,453Jul 2, 2025Updated 8 months ago
- [ICML2025] An 8-step inversion and 8-step editing process works effectively with the FLUX-dev model. (3x speedup with results that are coβ¦β288May 1, 2025Updated 10 months ago