chfm/Bernini-v2-ComfyUI

Bernini v2 is a video editor: t2v / i2v / v2v / r2v / rv2v / ads2v. The source media (reference images / source video) are first-class inputs. The pipeline has two stages:

1. Semantic planning: a fine-tuned Qwen2.5-VL (mllm) + connector + vit_decoder (MaskGIT-style loop) turn the text + source visual tokens into diff_mllm_contexts (the novel part Bernini-R lacks).
2. Rendering: two co-trained Wan2.2 DiTs (high-noise / low-noise, switched at 0.875) with the Bernini vae_txt_vit_wapg guidance (4-way CFG with APG projection), VAE-encoded source media as context_latents, Wan2.1 VAE decode.

ComfyUI Custom node

Extract the ZIP file in ComfyUI/custom_nodes

Task is inferred from which media inputs are connected: (none) = t2v, source_video = v2v, source_video + reference_images = rv2v, reference_images only = r2v, source_video + reference_video = ads2v.

Recommended settings

• CFG: 3
• Steps: 16, 23 or 50
• Sampler: UniPC / DPMPP_2M / EULER

Model files

• FP8_scaled

Place the planner files anywhere under models/text_encoders/ - folder names don't matters:

---