Ali-Yaser/Kandinsky-5.0-I2V-Lite-5s-lowvram

Habr | Project Page | Technical Report (soon) | Models🤗 | ComfyUI README

Kandinsky 5.0: A family of diffusion models for Video & Image generation

In this repository, we provide a family of diffusion models to generate a video or an image given a textual prompt and distilled model for faster generation.

Kandinsky 5.0 I2V Lite - FP8 (e4m3fn)

This is an FP8 (float8_e4m3fn) converted version of the original Kandinsky 5.0 I2V Lite model.

Details

• Original Model: kandinskylab/Kandinsky-5.0-I2V-Lite-5s
• Format: Safetensors (FP8 e4m3fn)
• Use Case: Reduced VRAM usage for ComfyUI and consumer GPUs.

Usage

Download diffusion_pytorch_model.safetensors and place it in your ComfyUI models/diffusion_models folder.