wuwukaka/ComfyUI-WanAnimatePlus

Seamless video connection and multi-reference image support for Wan Animate,Scail-2 and Wan Animate2

What it solves

ComfyUI-WanAnimatePlus enhances the WanVideo pipeline in ComfyUI by solving the problem of disjointed video segments and limited reference control. It enables the generation of seamless video continuations and allows for more precise guidance using multiple reference images, preventing the "degradation" often seen in long-form AI video generation.

How it works

The project introduces several specialized nodes and workflows to improve video consistency:

  • Multi-Reference Injection: The prefix_frames feature allows users to provide 1–5 additional reference images, which are encoded into the front of the generation canvas to guide the model.
  • Seamless Connection: The transition_video feature takes the last 21 frames of a previous video segment and injects them into the start of the new segment to ensure a smooth visual transition.
  • Model Support: It provides dedicated wrappers and samplers for Bernini, SCAIL-2, and Animate2 models, handling the complex conditioning (poses, masks, and reference images) required for these specific architectures.
  • Official Compatibility: It includes "Flow" nodes that use standard ComfyUI interfaces (MODEL, VAE, LATENT), allowing these advanced features to be integrated into official-style workflows.

Who it’s for

This tool is designed for ComfyUI users creating AI-generated videos who need high-temporal consistency, the ability to extend existing videos, or the capability to perform complex motion transfer and video editing using multiple reference sources.

Highlights

  • Multi-Reference Support: Use up to 5 reference images to better maintain identity and style.
  • Seamless Transitions: Hard-freeze the end of one clip to the start of another for continuous video generation.
  • Broad Model Compatibility: Integrated support for Bernini (v2v, r2v, t2v), SCAIL-2, and Animate2.
  • Advanced Sampling: Includes two-phase sampling and loop seam correction (auto_drift) to reduce visual glitches at segment boundaries.
  • Flexible Integration: Offers both "Easy" samplers for beginners and "Flow" nodes for advanced official-style workflow integration.

Related

  • Project
    AIMixer/ComfyUI_MiniMaxH3_Director

    A professional director's console for ComfyUI that streamlines long-form video generation using the MiniMax H3 model through a visual timeline and multi-segment management.

  • Project
    shiimizu/ComfyUI_smZNodes

    Custom ComfyUI nodes (CLIP Text Encode++ and Settings) that replicate AUTOMATIC1111's prompt parsing and embedding, enabling identical image generation between stable‑diffusion‑webui and ComfyUI.

  • Project
    YanWenKun/ComfyUI-Windows-Portable

    A ready‑to‑run Windows package that bundles ComfyUI (a node‑based UI for Stable Diffusion) with 40+ custom nodes and 300+ pre‑compiled Python packages, letting users launch AI image/video generation instantly on an NVIDIA GPU.

  • Project
    princepainter/ComfyUI-PainterI2V

    A ComfyUI node for Wan2.2 that fixes slow-motion issues in image-to-video generation by increasing motion amplitude and improving camera movement responsiveness.

  • Project
    Carasibana/ComfyUI-H3-FaceRefine

    ComfyUI‑H3‑FaceRefine adds custom nodes that detect, crop, re‑generate, and stitch back tiny faces in MiniMax H3 videos, fixing the model’s poor performance on small heads. It offers automatic and manual face‑selection workflows, robust tracking, optional cut detection, and integrates with existing MiniMax H3 pipelines.