Home Creators Posts Import Register Favorites Logout

Downloads

Content

Hey friends! 💛 I put together a dead-simple InfiniteTalk + WAN I2V setup so you can get talking-head video generation working in ComfyUI without guesswork. You’ll install ComfyUI, a few essential nodes, and grab the exact models this workflow expects. Everything’s below—just match the GGUF to your GPU VRAM and you’re golden.

One Click installer for my patreon supporters 💓:https://www.patreon.com/posts/comfyui-infinite-139122339

💻 Software

Get Git

If you haven’t already, install Git from here:https://git-scm.com/

ComfyUI — Generate video, images, audio, and more with a node graph.https://github.com/comfyanonymous/ComfyUI

Download and install.

Or If you are a 50XX Series User go here:https://github.com/comfyanonymous/ComfyUI

Download and Unzip.

ComfyUI-ManagerOpen the cmd while you are in your ComfyUI Folder under ComfyUI\custom_nodesgit clone https://github.com/Comfy-Org/ComfyUI-Manager.git

🧩 Must-have Custom Nodes

Install these from Inside ComfyUI After installing the manager:

KJNodeshttps://github.com/kijai/ComfyUI-KJNodes

rgthree-comfyhttps://github.com/rgthree/rgthree-comfy

VideoHelperSuitehttps://github.com/Kosinkadink/ComfyUI-VideoHelperSuite

MelBandRoFormer (node)https://github.com/kijai/ComfyUI-MelBandRoFormer

WanVideoWrapperhttps://github.com/kijai/ComfyUI-WanVideoWrapper

🧠 Pick the right GGUF for your VRAM8 GB → Q4_K_M → fallback Q3_K_M12 GB → Q5_K_M → fallback Q4_K_M16 GB → Q6_K → fallback Q5_K_M24 GB → Q6_K (MBR fp32)32 GB+ → Q8_0

📦 Models (what each is for)

😊 InfiniteTalk (GGUF) — Talking-head driver This is the core GGUF model that powers lip-sync and head motion generation from audio input. It listens to the audio and turns it into realistic mouth movements, facial animation, and subtle head nods. ➡️ Store in:models/diffusion_modelshttps://huggingface.co/Kijai/WanVideo_comfy_GGUF/tree/main/InfiniteTalk

📹WAN 2.1 I2V 14B 480p (GGUF) — Image-to-Video backboneProvides the motion engine that takes a still input frame and animates it into smooth video at 480p resolution. While InfiniteTalk handles facial sync, WAN I2V ensures natural motion and temporal coherence. ➡️ Store in: models/diffusion_modelshttps://huggingface.co/city96/Wan2.1-I2V-14B-480P-gguf/tree/main

⚡Lightx2v LoRA (Lightning 4-step) — Speed booster for I2VA distilled low-step LoRA that reduces the number of diffusion steps (down to ~4) while keeping quality. It makes the whole pipeline faster and more efficient, especially for long sequences. ➡️ Store in: models/lorashttps://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors?download=true

🧰 MelBandRoFormer (fp16 / fp32) — Vocal Separation ModelSeparates raw audio into vocals and instruments, ensuring a clean speech track for lip-sync. InfiniteTalk relies on this isolated voice to avoid background noise interference.➡️ Store in: models/diffusion_modelsfp16: optimized for GPUs up to ~24 GB VRAM.https://huggingface.co/Kijai/MelBandRoFormer_comfy/resolve/main/MelBandRoformer_fp16.safetensors?download=truefp32: more stable on larger setups with high VRAM.https://huggingface.co/Kijai/MelBandRoFormer_comfy/resolve/main/MelBandRoformer_fp32.safetensors?download=true

📜 UMT5-XXL (Text Encoder) — Prompt interpreterA massive text encoder (based on mT5 XXL) that converts written prompts into semantic embeddings. This lets the model understand and follow style, context, and conditioning beyond audio. ➡️ Store in: models/text_encodershttps://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp16.safetensors?download=true

🖼️ CLIP-Vision H — Visual encoderProcesses input frames or reference images to ensure the animated video remains faithful to the original identity and composition. ➡️ Store in: models/clip_visionhttps://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors

🛠️WAN 2.1 VAE — Latent encoder/decoderThe VAE compresses frames into latents for efficient processing and reconstructs them into visuals. Using the repackaged WAN VAE ensures maximum compatibility. ->models/vaehttps://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors?download=true

🧰 Tencent Wav2Vec2 (Base) — Speech Embedding ModelExtracts speech embeddings from the clean vocal track. These embeddings capture phoneme- and prosody-like features, which InfiniteTalk uses to generate accurate mouth shapes and timing.No Download link. This will be downloaded on runtime.

👉 TL;DR flow

1. Install ComfyUI + ComfyUI-Manager2. Add the listed custom nodes3. Download the models above4. Launch InfiniteTalk, feed text/audio, and render

Files

Mind-blowing Lip-Sync Animated Avatar - UNCENSORED Text To Speech

Meet Aurelia—an animated, lip-sync avatar built in ComfyUI with Infinite Talk and WAN Video. In this step-by-step guide I show you the exact workflow, required custom nodes, model placements, and how to supercharge speed with SageAttention. We’ll cover single-speaker first, then jump to multi-speaker setups, plus audio generation (TTS) and practical troubleshooting for red boxes and nightly builds. Want the one-click installer, workflows, and my VRAM download guide? They’re on my Patreon—so you can go from zero to talking avatar with minimal fuss. 📅 Book Your Personal 1-on-1 Session: 👉 Schedule Here: https://koalendar.com/e/1hr-1-on-1-stable-diffusion 🎁 Free Goodies & Essential Resources: • 🎯 Ultimate Beginner's Guide: https://www.patreon.com/posts/sneak-peek-alert-90799508 • 🛠️ Free Workflow Guide: https://www.patreon.com/posts/get-your-free-99183367 • 🎨 My Exclusive Style Collection: https://www.patreon.com/posts/my-collection-of-87325880 • 🚀 Support & Get Exclusive Content: 👉 Join Patreon Community: https://patreon.com/AIKnowledgeCentral 🎬 Popular Playlists: • 🤖 Invoke AI: Watch Here: https://www.youtube.com/watch?v=70HTvc-4gek&list=PL8HbYkSF5f9Ggts03f7ttPzFJyFiHgqoJ • ⚡ Flux: Watch Here: https://www.youtube.com/watch?v=70HTvc-4gek&list=PL8HbYkSF5f9Ggts03f7ttPzFJyFiHgqoJ • 🛠️ Forge: Watch Here: https://www.youtube.com/watch?v=70HTvc-4gek&list=PL8HbYkSF5f9Ggts03f7ttPzFJyFiHgqoJ • 🎨 ComfyUI: Watch Here: https://www.youtube.com/watch?v=70HTvc-4gek&list=PL8HbYkSF5f9Ggts03f7ttPzFJyFiHgqoJ • 🖥️ Automatic 1111: Watch Here: https://www.youtube.com/watch?v=70HTvc-4gek&list=PL8HbYkSF5f9Ggts03f7ttPzFJyFiHgqoJ • 📌 AI Tools: Watch Here: https://www.youtube.com/watch?v=70HTvc-4gek&list=PL8HbYkSF5f9Ggts03f7ttPzFJyFiHgqoJ 🌎Civitai: https://civitai.com/user/AIknowlege2go Chapters 00:00 Intro 03:18 Lip-Sync Avatar 08:45 Multi-Talk 12:21 NSFW Audio

Comments

Da elks

used the one click installer. It failed to most of the files needed. Bit frustrating , Any idea why? thanks

Iain Forbes

Anyway to combine InfiniteTalk with an existing input video?

Iain Forbes

Hi Chris I can't seem to get this passed WanVideoSampler. It sticks at that. Which is 75% through the whole process but 0% through WanVideoSampler. I've tried changing the blocks to swap value to 40 but it didn't make a difference. Same with lowering the resolution of the source image. I've also tried q5km and q4km to no avail. any help would be appreciated

AI Knowledge Central

Hi, could you try to lower the output resolution or the length of the audio file? so that you get a "quick" test. Dm me if that problem persists.

Iain Forbes

I'll give both a try! Thanks

Niko Louvranos

Hi Chris, any chance for this workflow to: 1. move to wan2.2 (better LoRa support, higher quality) 2. include Spanish language lip sync. Currently it doesn't work well with Spanish audio (I assume due to the Chinese wan2vec2 model

Niko Louvranos

I found the same but no clue how to use it. No worries! Thanks!

anonimoose

Howdy, Getting an error in the WanVideoSampler. RuntimeError: shape '[20, 182, 5120]' is invalid for input of size 19389440