InfiniteTalk (MultiTalk 2.0) with Wan 2.1 : 5 Steps Video 2 Video with GGUF Support — v1.0
v 1.0
Runtime profile
- Access
- External workflow
- Status
- Listed
- Version
- Wanvideo_V2V_InfiniteTalk_RareTutor.json
- Source
- Civitai
- Updated
- Oct 18, 2026
What you need
- Model files
- 17.3 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Requirements
Models
8clip_vision_h.safetensors
PossibleVision model · Unknown
infinitetalk_single.safetensors
Not resolvedCheckpoint · Unknown
LoRA · 1.37 GB · SAFETENSOR · Civitai · 1585622
lightx2v_I2V_14B_720p_cfg_step_distill_rank64.safetensors
PossibleLoRA · Unknown
Checkpoint · Hugging Face · TencentGameMate/chinese-wav2vec2-base
umt5-xxl-enc-fp8_e4m3fn.safetensors
PossibleCheckpoint · Unknown
Checkpoint · 15.5 GB · Hugging Face · Kijai/WanVideo_comfy_fp8_scaled
- Possible
VAE · 484 MB · Hugging Face · DeepBeepMeep/Wan2.1
Node packs
4Node pack · Registry
- Found
Node pack · Registry
Node pack · Registry
Node pack · Registry
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Purpose
Use this five-step video-to-video workflow with InfiniteTalk (MultiTalk 2.0) and Wan 2.1: it takes video in and produces video out; the listing also tags image-to-video use.
Flow
The graph includes nodes for loading video and audio, separating audio, processing with MultiTalk and Wan nodes, previewing audio and images, and combining video.
Inputs and outputs
The listing does not specify supported input or output file formats.
Setup
The v1.0 download is a ZIP archive containing a workflow JSON file; the listing includes no model-weight artifacts.
Dependencies
Model files named for the workflow include clip_vision_h.safetensors, infinitetalk_single.safetensors, lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16.safetensors, and lightx2v_I2V_14B_720p_cfg_step_distill_rank64.safetensors.
Other named model files are TencentGameMate/chinese-wav2vec2-base, umt5-xxl-enc-fp8_e4m3fn.safetensors, Wan2_1-I2V-14B-720p_fp8_e5m2_scaled_KJ.safetensors, and Wan2.1_VAE.safetensors.
The graph lists four node packs: audio-separation-nodes-comfyui, comfyui-kjnodes, comfyui-videohelpersuite, and ComfyUI-WanVideoWrapper.
Configuration
The listing names Wan Video 14B i2v 720p as its base model and advertises GGUF support.
Cautions
Before setup, verify you can obtain the listed model files and install the four node packs; several named model files have no download URL in the listing details.
Suggestion
Does this need to be edited?
Sign in to send an edit request.
Sources
1 source
Sources
1 sourceSource excerpts
3 excerpts
Source excerpts
3 excerptsSource context: 1034 downloads · Type Workflows · Base model Wan Video 14B i2v 720p
Source context: 949 downloads · Type Workflows · Base model Wan Video 14B i2v 720p
Source context: 925 downloads · Type Workflows · Base model Wan Video 14B i2v 720p
