instantX-research / InstantIR
InstantIR: Blind Image Restoration with Instant Generative Reference π₯
β504Updated 5 months ago
Alternatives and similar repositories for InstantIR:
Users that are interested in InstantIR are comparing it to the libraries listed below
- A set of nodes to edit videos using the Hunyuan Video modelβ449Updated 2 months ago
- [NeurIPS 2024] Generalizable Implicit Motion Modeling for Video Frame Interpolationβ286Updated 5 months ago
- Enhance-A-Video: Better Generated Video for Freeβ509Updated last month
- A set of ComfyUI nodes providing additional control for the LTX Video modelβ481Updated last month
- β404Updated 5 months ago
- Lumina-Image 2.0: A Unified and Efficient Image Generative Frameworkβ663Updated this week
- β778Updated 5 months ago
- β671Updated this week
- π₯π₯ UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioningβ876Updated last week
- πΉ A more flexible framework that can generate videos at any resolution and creates videos from images.β926Updated this week
- Training-free Regional Prompting for Diffusion Transformers π₯β626Updated 4 months ago
- β581Updated this week
- Phantom: Subject-Consistent Video Generation via Cross-Modal Alignmentβ679Updated this week
- β1,023Updated this week
- A pipeline parallel training script for diffusion models.β937Updated this week
- Illumination Drawing Tools for Text-to-Image Diffusion Modelsβ726Updated 4 months ago
- HunyuanVideo GP: Large Video Generation Model - GPU Poor versionβ399Updated 3 weeks ago
- A port of muerrilla's sd-webui-Detail-Daemon as a node for ComfyUI, to adjust sigmas that control detail.β669Updated last month
- β494Updated last month
- A minimal and universal controller for FLUX.1.β1,509Updated this week
- Official implementation of "FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on"β523Updated 2 months ago
- Nodes for image juxtaposition for Flux in ComfyUIβ1,265Updated 3 months ago
- Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"β591Updated 3 months ago
- β365Updated 5 months ago
- [ICLR'25] Official PyTorch implementation of "Framer: Interactive Frame Interpolation".β463Updated 3 months ago
- β516Updated 3 months ago
- [768 Resolution] [Any "SDXL" Model] [Various Conditions] [Arbitrary Views] Official impl. of "MV-Adapter: Multi-view Consistent Image Genβ¦β882Updated this week
- JoyCaption is an image captioning Visual Language Model (VLM) being built from the ground up as a free, open, and uncensored model for thβ¦β423Updated 4 months ago
- Light-A-Video: Training-free Video Relighting via Progressive Light Fusionβ408Updated 2 weeks ago
- High quality training free inpaint for every stable diffusion model.β248Updated this week