2:560:54Image preparation for InfiniteTalkThe video shows the process of loading a portrait image and resizing it to the specific 384x640 resolution required by the Wan video model using standard ComfyUI nodes.ComfyUI· AI Crop Image
3:503:32Setting up Wan 2.1 and InfiniteTalk modelsA walkthrough of the model group in ComfyUI, showing the configuration of Wan Video Block Swap for VRAM management, the Light X2V LoRA for faster generation, and the InfiniteTalk GGUF model for audio conditioning.ComfyUI· AI Animation Generator
9:081:03Sampling and video output generationThe demonstration shows the final sampling process using the Lightning LoRA settings (CFG 1, 7-10 steps) and combining the decoded frames with audio for the final video file.ComfyUI· AI Animation Generator
2:560:54Image preparation for InfiniteTalkThe video shows the process of loading a portrait image and resizing it to the specific 384x640 resolution required by the Wan video model using standard ComfyUI nodes.ComfyUI· AI Crop Image