ai-forever / Kandinsky-4
Text and image to video generation: Kandinsky 4.0 (2024)
☆144Updated 4 months ago
Alternatives and similar repositories for Kandinsky-4:
Users that are interested in Kandinsky-4 are comparing it to the libraries listed below
- Pusa: Thousands Timesteps Video Diffusion Model☆153Updated last week
- Scale-wise Distillation of Diffusion Models☆89Updated last week
- [CVPR 2025] Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models☆182Updated 3 weeks ago
- ☆236Updated last month
- The best OSS video generation models☆132Updated 5 months ago
- LayerAnimate: Layer-specific Control for Animation☆152Updated 3 weeks ago
- Keyframe Interpolation with CogvideoX☆126Updated 5 months ago
- The official implementation of ”RepVideo: Rethinking Cross-Layer Representation for Video Generation“☆116Updated 2 months ago
- Inference-time scaling of diffusion-based image and video generation models.☆136Updated last month
- ☆152Updated last week
- Official PyTorch Implementation of "Optimal Stepsize for Diffusion Sampling".☆139Updated last week
- ☆148Updated 2 weeks ago
- SkyReels-V2: Infinite-length Film Generative model☆853Updated this week
- (CVPR 2025) Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis☆177Updated last month
- ☆78Updated last month
- [NeurIPS 2024] RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance☆125Updated 6 months ago
- [ECCV 2024] Be-Your-Outpainter https://arxiv.org/abs/2403.13745☆239Updated this week
- faster parallel inference of mochi-1 video generation model☆117Updated last month
- IP Adapter Instruct☆204Updated 8 months ago
- Official implement of ID-Aligner☆122Updated 11 months ago
- Code repository for T2V-Turbo and T2V-Turbo-v2☆296Updated 2 months ago
- KandinskyVideo — multilingual end-to-end text2video latent diffusion model☆184Updated 10 months ago
- Video-Infinity generates long videos quickly using multiple GPUs without extra training.☆179Updated 8 months ago
- Paint by Inpaint: Learning to Add Image Objects by Removing Them First☆100Updated 2 weeks ago
- [CVPR 2025] Consistent and Controllable Image Animation with Motion Diffusion Models☆266Updated 2 weeks ago
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆210Updated 3 months ago
- Pytorch implementation of MIMO, Controllable Character Video Synthesis with Spatial Decomposed Modeling, from Alibaba Intelligence Group☆132Updated 6 months ago
- ☆22Updated this week
- CogVideoX-LoRAs is a centralized repository for all LoRA models created for CogVideoX, filling the gap for a unified sharing space. With …☆79Updated 4 months ago
- CVPR2025:AnimateAnything☆168Updated last month