UPDATE TO THE LATEST COMFY!

Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

On video editing, Bernini reaches the first tier among leading closed-source commercial models.



HIGH and LOW Diffusion Model (REQUIRES BOTH MODELS)

https://huggingface.co/neuregex/Bernini-R-GGUF/tree/main

Text Encoder

https://huggingface.co/Osrivers/umt5_xxl_fp8_e4m3fn_scaled.safetensors/tree/main

VAE
https://huggingface.co/QuantStack/Wan2.2-I2V-A14B-GGUF/tree/main/VAE

LoRA (REQUIRED FOR DISTILLATION STEP COUNT)
https://huggingface.co/lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill-Lightx2v/tree/main/loras