demobook

Configure Infinite Talk models in ComfyUI

ComfyUITry it →Watch full video →Aiconomist ·

Demo summary

The creator demonstrates how to organize the necessary models within the ComfyUI workflow, including the Lightning LoRA, quantized Infinite Talk UNET models, and the Wan 2.1 VAE and Clip Vision nodes.

Step-by-step

  1. Open the Infinite Talk example workflow in ComfyUI
  2. Download the Lightning LoRA and save it in the Lora's folder
  3. Download a quantized version of the Infinite Talk model and place it in the UNET folder
  4. Add the Wan 2.1 VAE and Clip Vision H models to the workflow
  5. Add the Clip Text Encoder using a GGUF version
  6. Change the precision setting to BF16 if your GPU does not support FP16 fast

Options

  • Use Q6 or Q8 quantized models for 24 GB VRAM
  • Use Q4 quantized models for 12 to 16 GB VRAM
  • Switch from FP16 fast to BF16 for older GPU support

Watch out for

  • The Clip Vision H model is required because this is an image-to-video process
  • Infinite Talk models must be placed specifically in the UNET folder

Tips

  • Use a GGUF version of the clip text encoder that suits your GPU's capacity
  • Users with lower-tier GPUs should aim for the Q4 model to avoid insufficient VRAM messages

All demos from “Create UNLIMITED Talking Videos with InfiniteTalk! (ComfyUI Tutorial)”

  1. 2:351:46Configure Infinite Talk models in ComfyUICurrentThe creator demonstrates how to organize the necessary models within the ComfyUI workflow, including the Lightning LoRA, quantized Infinite Talk UNET models, and the Wan 2.1 VAE and Clip Vision nodes.ComfyUIAI Animation Generator
  2. 5:081:06Setting input image and frame parametersThe video shows how to load a source image into the ComfyUI workflow and adjust resolution and maximum frame settings based on GPU VRAM capacity.ComfyUIAI Image Generator
  3. 6:490:36Refining output with positive promptsThe demo shows how to use positive text prompts in ComfyUI to maintain visual consistency, such as fixing changing nail colors on the animated character.ComfyUIAI Image Generator
  4. 7:580:38Generating the final talking videoThe creator shows the KSampler settings using Lightning LoRA for fast 7-step generation and displays the final 53-second talking head result.ComfyUIAI Avatar Video Generator
  5. Watch “Create UNLIMITED Talking Videos with InfiniteTalk! (ComfyUI Tutorial)” →

AI Animation Generator

  1. 2:070:23Load Wan 2.2 Animate workflow and install nodesThe user demonstrates how to drag and drop the Wan 2.2 Animate workflow into ComfyUI and use the Manager to install missing custom nodes.MDMZ
  2. 2:551:05Configure video input and output settingsThe demo shows how to upload a source video to ComfyUI, set the frame count, and adjust the output dimensions to match the original aspect ratio.MDMZ
  3. 16:361:56Setting up HunyuanVideo 1.5 in ComfyUIThe video demonstrates how to update ComfyUI and import the HunyuanVideo 1.5 JSON workflow files to create a node-based generation environment.AI Search
  4. 20:151:53Text-to-Video generation in ComfyUIA step-by-step demo of configuring the Hunyuan nodes in ComfyUI, entering a prompt for a 'giant cat', and rendering the final 720p video.AI Search
  5. 29:151:33Running HunyuanVideo with GGUF (Low VRAM)The video shows how to use the GGUF loader node to run a compressed version of HunyuanVideo 1.5, enabling video generation on GPUs with as little as 6GB of VRAM.AI Search
  6. 0:594:52Configure LTX 2.3 in ComfyUIThe creator walks through the ComfyUI node setup for LTX 2.3, explaining the GGUF model loader, VAE settings, and how to adjust resolution and frame counts for optimal rendering.AIKnowledge2Go
  7. 1:230:41Setting up LTX-2.3 in ComfyUIThe creator demonstrates how to browse templates in ComfyUI, search for LTX 2.3, and download the required missing models for the text-to-video workflow.MDMZ
  8. 13:071:21Applying LoRA to Wan 2.2 video generationThe video shows how to integrate a LoRA (Low-Rank Adaptation) into a Wan 2.2 workflow to achieve specific cinematic movements like a face zoom.pixaroma
  9. 31:133:44Text-to-video with LTX-2The video walks through setting up the LTX-2 model in ComfyUI to generate high-resolution video clips from text prompts and images.pixaroma
  10. 39:075:27Cloud-based ComfyUI on RunPod/RunHubThe video shows how to run complex video workflows in the cloud using RunHub AI, demonstrating the interface and execution of InfiniteTalk and Wan 2.2 without local hardware.pixaroma
  11. 2:351:46Configure Infinite Talk models in ComfyUICurrentThe creator demonstrates how to organize the necessary models within the ComfyUI workflow, including the Lightning LoRA, quantized Infinite Talk UNET models, and the Wan 2.1 VAE and Clip Vision nodes.Aiconomist
  12. 11:060:26Combining audio, images, and promptsA demonstration of layering a specific action prompt (patting stomach) over a specific audio timestamp to create a fully directed AI scene.What Dreams Cost
demobook

Show, don’t tell.

Categories

Video & AnimationImage Generation & EditingSales TechEmail Marketing

About

SubmitAboutPrivacyTermsContact

© demobook.co