Image-Text-to-Video
Wan2.2
text-to-video
video-to-video
image-to-video
wan2.1
bernini
fp8
comfyui
scaled-fp8
Instructions to use Abiray/Wan22_Bernini_FP8_Scaled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Wan2.2
How to use Abiray/Wan22_Bernini_FP8_Scaled with Wan2.2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
| base_model: ByteDance/Bernini-R | |
| base_model_relation: quantized | |
| license: apache-2.0 | |
| tags: | |
| - text-to-video | |
| - video-to-video | |
| - image-to-video | |
| - wan2.1 | |
| - wan2.2 | |
| - bernini | |
| - fp8 | |
| - comfyui | |
| - scaled-fp8 | |
| pipeline_tag: image-text-to-video | |
| # Wan22_Bernini_FP8_Scaled | |
| This repository contains optimized FP8 Scaled (`e4m3fn`) checkpoints for **Bernini-R**, a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer. | |
| These weights are derived from ByteDance's raw transformer checkpoints (`ByteDance/Bernini-R`) and have been fully calculated with accurate inverse scale tensors using the optimization pipeline popularized by Kijai. This allows high-quality inference in ComfyUI with dramatically reduced VRAM overhead while fully preserving the dynamic range of the original model layers. | |
| ## π¦ Model Information | |
| * **Architecture:** Diffusion Transformer (DiT) based on Wan 2.2 | |
| * **Precision:** FP8 (`e4m3fn`) with Custom Scaled Coefficients | |
| * **File Types Included:** | |
| * `Wan22_Bernini_HIGH_fp8_e4m3fn_scaled.safetensors` (~15.6 GB) β Optimized high-noise diffusion layers. | |
| * `Wan22_Bernini_LOW_fp8_e4m3fn_scaled.safetensors` (~15.6 GB) β Optimized low-noise refining layers. | |
| --- | |
| ## π οΈ ComfyUI Integration & Usage | |
| Unlike naive FP8 conversions that truncate model data and cause color saturation artifacts, these weights include per-tensor scale matrices that native ComfyUI nodes can interpret directly. | |
| ### Prerequisites | |
| Make sure your ComfyUI architecture is fully up to date to support native Wan 2.2 scaling structures. You will need the core tracking node wrappers or advanced custom nodes (such as `Kijai/ComfyUI-WanVideoWrapper`) to load the High/Low handoff pipeline. | |
| ### Directory Setup | |
| Place both downloaded `.safetensors` files into your default ComfyUI checkpoint or diffusion model directory: | |
| ```text | |
| ComfyUI/models/checkpoints/ | |
| βββ Wan22_Bernini_HIGH_fp8_e4m3fn_scaled.safetensors | |
| βββ Wan22_Bernini_LOW_fp8_e4m3fn_scaled.safetensors |