❤️ If you enjoy my work and would like to support me, consider buying me a ☕ Coffee .
Perfil de execução
Descrição da fonte
❤️ If you enjoy my work and would like to support me, consider buying me a ☕ Coffee .
Animate any character image using a reference/guiding video — transfer motion, swap characters, or recreate performances with your own subject. Powered by the Wan2.1 14B SCAIL V2 model with SAM3 for pose detection and subject isolation.
⚠️ Custom Node Disclaimer
This workflow heavily utilizes custom nodes. Manually modifying the ComfyUI file system or improperly managing node installations can break your ComfyUI environment. Ensure you understand how to manage dependencies and custom node directories before altering the underlying installation to prevent conflicts or system instability. If you are unfamiliar with these topics, please make a backup of your ComfyUI setup before installing new nodes or updating ComfyUI. For beginners, I generally recommend using the portable version, as it is easier to maintain and back up.
Comentário gerado por IA
Explicação gerada por IA com base nos detalhes da fonte e da configuração. As sugestões são claramente identificadas.
Use this workflow to animate any character image from a reference or guiding video, transferring motion, swapping characters, or recreating a performance for one or more characters. It can output a standalone animated clip or replace a character within the guiding video.
SAM3 provides pose detection and can isolate a subject from the guiding video using a text description.
For long videos, overlapping batch windows are used alongside a high-res fix pass, NVIDIA VSR upscaling, and RIFE frame interpolation.
Inputs include a character image, a reference or guiding video, and optionally a text description for subject isolation.
The output can carry the original audio or use custom audio from an audio file or video source.
Use ComfyUI nightly because newer core nodes used by the workflow may not be available in the stable release.
Sugestão · não verificado
Install the latest versions of KJNodes, ComfyUI Essentials, rgthree-comfy, and ComfyUI-Frame-Interpolation.
Sugestão · não verificado
The workflow lists these model filenames: wan2.1_14B_SCAIL_2_fp8_scaled.safetensors, lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors, wan_2.1_vae.safetensors, clip_vision_h.safetensors, sam3.1_multiplex_fp16.safetensors, and umt5_xxl_fp8_e4m3fn_scaled.safetensors.
Node-pack names listed include: comfyui-custom-scripts, comfyui-kjnodes, comfyui-impact-pack, comfyui-resolution-master, comfyui-easy-use, and crt-nodes.
Additional node-pack names are: comfyui-frame-interpolation, rgthree-comfy, comfyui_layerstyle, comfyui_nvidia_rtx_nodes, and comfyui-videohelpersuite.
Choose standalone generation or replacement mode, and use the Power LoRA node to add Wan2.1-compatible character, concept, or style LoRAs.
Sugestão · não verificado
Yellow nodes are configurable, while red nodes contain instructions and useful notes.
Back up your ComfyUI setup before installing or updating custom nodes. If you use the portable NVIDIA VSR fix, back up the embedded Python directory first.
Sugestão · não verificado
If ComfyUI Manager reports a security-level error for ComfyUI_NVIDIA_RTX_Nodes, confirm the link is https://github.com/Comfy-Org/Nvidia_RTX_Nodes_ComfyUI, temporarily set security_level = weak, hard-restart ComfyUI, then restore the original setting and restart again.
Sugestão · não verificado
Isso precisa ser editado?
Faça login para enviar uma solicitação de edição.
Fontes
1 fonteTrechos de fonte
3 trechosSource context: 812 downloads · Type Workflows · Base model Wan Video 14B i2v 480p
Prerequisites
⚠️ ComfyUI nightly — this workflow uses newer core nodes that might not be available in the stable release yet depending on when you read this.
The following custom node packs, all updated to their latest version:
KJNodes
ComfyUI Essentials
rgthree-comfy
ComfyUI-Frame-Interpolation (for the RIFE interpolation group)
Key Features
Motion transfer / character swap : animate your character with the motion from any reference video, supports single and multiple characters.
SAM3 subject isolation : isolate specific subjects from the guiding video using a simple text description.
Replacement mode (character swap): optionally replace the original character within the guiding video instead of generating a standalone clip.
Batched generation: handles long videos via overlapping batch windows for smooth, seamless output.
LoRA support: A Power LoRA node allows you to easily add character, concept and style Wan2.1 compatible LoRAs.
High-res fix pass : a second sampling pass at a higher resolution for improved detail.
NVIDIA VSR upscaling : GPU-accelerated video upscaling.
RIFE VFI interpolation : smooth out the frame rate with RIFE frame interpolation.
Audio : carries the original audio through to the final output, or a custom audio from an audio file or video source.
COMFYUI SECURITY ERROR FIX
If you hit a security level error while trying to install the ComfyUI_NVIDIA_RTX_Nodes custom node from ComfyUI manager:
You need to temporarily change the security level in your config.ini file.
If you are using the portable version, the file is located at: ComfyUI/user/__manager/config.ini
Change the value to: security_level = weak
IMPORTANT: Do NOT forget to restore it back to its original value. It is safe to temporarily lower the security level for this node since it comes directly from the ComfyUI team, but you should restore it afterward for safety reasons.
Perform a hard restart of ComfyUI (completely stop it, then start it again).
Install the custom node using ComfyUI manager and double-check that it is the official one. The link should point to: https://github.com/Comfy-Org/Nvidia_RTX_Nodes_ComfyUI
Restart ComfyUI and check if the node works properly. If you encounter a dependency error, keep reading...
Once everything is working properly, restore your original security level in the config.ini file and restart ComfyUI one final time.
COMFYUI PORTABLE DEPENDENCY ERROR FIX
If you hit a dependency error trying to run the Nvidia VSR node, try this: Create a backup of your embedded Python directory, in case you break something you can restore your embedded directory later using this backup. Then run the following command:
python -m pip install -U --no-build-isolation nvidia-vfx --index-url https://pypi.nvidia.com
Run the command in your embedded Python directory. For example: D:\ComfyUI\python_embeded. This command is designed for CMD. If you're using PowerShell, replace the initial python with .\python.exe.
Detailed instructions are contained in the workflow itself:
Red nodes are instructions and useful notes.
Yellow nodes are configurable elements you can adjust to your needs.
Estimativa de requisito VRAM
Estimativa indisponível
16,5 GB distribuídos em 1 de 6 arquivos de modelo. Total de arquivos do modelo + 25% de overhead de carregamento + 2 GB de buffer de execução, arredondado para cima.
Requisitos
Requisitos 17Vision model · Unknown
lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors
ConflitoLoRA · Unknown
Fontes possíveis
sam3.1_multiplex_fp16.safetensors
ConflitoCheckpoint · Unknown
umt5_xxl_fp8_e4m3fn_scaled.safetensors
Arquivo não verificadoText encoder · SAFETENSORS · Unknown
VAE · Unknown
Checkpoint · 16.5 GB · SAFETENSORS · Unknown
Pacote de nós · Registry
comfyui_nvidia_rtx_nodes
Não resolvidoPacote de nós · Registry
Source context: 805 downloads · Type Workflows · Base model Wan Video 14B i2v 480p
Source context: 697 downloads · Type Workflows · Base model Wan Video 14B i2v 480p
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry