ai-forever / deforum-kandinskyLinks
Kandinsky x Deforum — generating short animations
☆105Updated last year
Alternatives and similar repositories for deforum-kandinsky
Users that are interested in deforum-kandinsky are comparing it to the libraries listed below
Sorting:
- ☆60Updated last year
- Text and image to video generation: Kandinsky 4.0 (2024)☆146Updated 9 months ago
- Apply controlnet to video clips☆80Updated 11 months ago
- ☆25Updated last year
- Implementation of "SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing"☆85Updated last year
- Repository with which to explore k-diffusion and diffusers, and within which changes to said packages may be tested.☆52Updated last year
- ☆61Updated last year
- ☆51Updated 2 years ago
- Let's try and finetune the OpenAI consistency decoder to work for SDXL☆24Updated last year
- KandinskyVideo — multilingual end-to-end text2video latent diffusion model☆183Updated last year
- Towards Robust Blind Face Restoration with Codebook Lookup Transformer☆32Updated last year
- ☆69Updated 11 months ago
- ControlAnimate Library☆48Updated last year
- Gradio app to track objects in video and add visual effects☆17Updated 2 months ago
- Open-Sora: Democratizing Efficient Video Production for All☆19Updated 11 months ago
- ☆25Updated last year
- Kandinsky 2 — multilingual text2image latent diffusion model☆74Updated 2 years ago
- ☆24Updated last year
- Generate images from an initial frame and text☆37Updated 2 years ago
- SliderSpace: Decomposing the Visual Capabilities of Diffusion Models☆101Updated last week
- ☆79Updated last year
- ☆17Updated last year
- ☆21Updated last year
- [NOTE] I do not have enough ressources to maintain VMS, please use Ostris's AI-Tookit instead☆39Updated last week
- lightweight LAMA inference wrapper☆26Updated 2 years ago
- Pytorch implementation of MIMO, Controllable Character Video Synthesis with Spatial Decomposed Modeling, from Alibaba Intelligence Group☆135Updated last year
- ☆54Updated last year
- Build your own Face App with Stable Diffusion 2.1☆152Updated 9 months ago
- SSD-1B, an open-source text-to-image model, outperforming previous versions by being 50% smaller and 60% faster than SDXL.☆176Updated last year
- ☆18Updated last year