ai-forever / Kandinsky-5Links
Kandinsky 5.0: A family of diffusion models for Video & Image generation
☆167Updated this week
Alternatives and similar repositories for Kandinsky-5
Users that are interested in Kandinsky-5 are comparing it to the libraries listed below
Sorting:
- (CVPR 2025) Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis☆195Updated 3 months ago
- Text and image to video generation: Kandinsky 4.0 (2024)☆147Updated 10 months ago
- Scale-wise Distillation of Diffusion Models☆112Updated last month
- This is the official implementation of "T-LoRA: Single Image Diffusion Model Customization Without Overfitting"☆122Updated 3 months ago
- Making Flux go brrr on GPUs.☆146Updated 3 months ago
- Official Implementation for "Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing"☆54Updated last year
- Wan: Open and Advanced Large-Scale Video Generative Models☆21Updated 2 months ago
- ☆31Updated 4 months ago
- Inference-time scaling of diffusion-based image and video generation models.☆169Updated 3 months ago
- Official Implementation for "The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Ed…☆106Updated last year
- ☆21Updated 2 years ago
- Official PyTorch Implementation of "Optimal Stepsize for Diffusion Sampling".☆190Updated 6 months ago
- DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space☆245Updated 2 weeks ago
- [NeurIPS'2024] Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps☆100Updated last year
- Scripts to teach Flux the task of image editing from language with the Flux Control framework.☆94Updated 3 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 co…☆278Updated 5 months ago
- Krea Realtime 14B. An open-source realtime AI video model.☆175Updated this week
- [CVPR 2025] Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models☆307Updated 4 months ago
- ☆171Updated last month
- Tiny AutoEncoder for Hunyuan Video (and other video models)☆189Updated last month
- The official code for "MagCache: Fast Video Generation with Magnitude-Aware Cache"☆213Updated last month
- [NeurIPS 2024] RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance☆129Updated last year
- Home Made Diffusion Models☆160Updated last month
- ☆160Updated last week
- Generate long weighted prompt embeddings for Stable Diffusion☆139Updated 6 months ago
- ☆104Updated last month
- [ICCV 2025] Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning☆199Updated 3 months ago
- Kandinsky x Deforum — generating short animations☆104Updated last year
- KandinskyVideo — multilingual end-to-end text2video latent diffusion model☆182Updated last year
- Nitro-T is a family of text-to-image diffusion models focused on highly efficient training.☆29Updated 3 months ago