PKU-YuanGroup / ConsisID
[CVPR 2025π₯] Identity-Preserving Text-to-Video Generation by Frequency Decomposition
β656Updated this week
Alternatives and similar repositories for ConsisID:
Users that are interested in ConsisID are comparing it to the libraries listed below
- Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement π₯β555Updated 2 months ago
- Codes for ID-Specific Video Customized Diffusionβ453Updated last year
- [CVPR'25]Tora: Trajectory-oriented Diffusion Transformer for Video Generationβ1,110Updated last month
- The official implementation of RealisDanceβ318Updated 4 months ago
- Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Modelsβ908Updated 2 weeks ago
- Video generation from text&image, 1st-genβ842Updated last month
- β826Updated 3 months ago
- Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers"β515Updated last month
- Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformerβ1,162Updated 3 weeks ago
- Code for SCIS-2025 Paper "UniAnimate: Taming Unified Video Diο¬usion Models for Consistent Human Image Animation".β1,062Updated 8 months ago
- β151Updated 10 months ago
- [ECCV 2024 Oral] MotionDirector: Motion Customization of Text-to-Video Diffusion Models.β936Updated 7 months ago
- [Arxiv 2024] From Parts to Whole: A Unified Reference Framework for Controllable Human Image Generationβ180Updated 8 months ago
- Official repo of our paper "SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions"β609Updated 10 months ago
- [ICLR 2025] Official implementation of MotionClone: Training-Free Motion Cloning for Controllable Video Generationβ471Updated 3 months ago
- Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple teβ¦β1,066Updated last month
- [ECCV 2024] Bridging Different Language Models and Generative Vision Models for Text-to-Image Generationβ290Updated 8 months ago
- Pytorch Implementation of FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing (ICLR 2024)β205Updated 10 months ago
- a family of versatile and state-of-the-art video tokenizers.β355Updated last week
- NeurIPS 2024β362Updated 6 months ago
- Official implementation for "Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model" (NeurIPS 2024)β252Updated 5 months ago
- [NeurIPS 2023] Official implementations for paper: Customizable Image Synthesis with Multiple Subjectsβ431Updated last year
- [AAAI 2025] Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image Generationβ129Updated 3 months ago
- Video-Inpaint-Anything: This is the inference code for our paper CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Cβ¦β281Updated 6 months ago
- β514Updated 2 months ago
- A work list of recent human video generation method. This repository focus on half/full body human video generation method, The Nerf, Gauβ¦β221Updated 5 months ago
- [ICLR'25] 3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generationβ321Updated last month
- UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalizationβ242Updated 5 months ago
- [CVPR 2025] The First Investigation of CoT Reasoning in Image Generationβ575Updated last week
- Light-A-Video: Training-free Video Relighting via Progressive Light Fusionβ398Updated 2 weeks ago