COMFYUI WORKFLOW GUIDE

Wan 2.2 in ComfyUI: From Download to First Render

Wan 2.2's open weights (Apache 2.0) run locally on consumer GPUs via ComfyUI's native workflow templates. This guide covers the exact files, folders and settings for your first successful render — and when to skip local setup and use the API instead.

Step 1: Use the Built-In Workflow Templates

ComfyUI ships Wan 2.2 workflows in its template library — no manual node wiring required. Open ComfyUI and go to Workflow → Browse Templates → Video, then load 'Wan2.2 14B T2V' for text-to-video, 'Wan2.2 14B I2V' for image-to-video, or 'Wan2.2 5B' for the lightweight hybrid model.

The 14B models use a two-expert MoE architecture (high-noise and low-noise experts) that ComfyUI loads sequentially, keeping peak VRAM under 24GB.

Step 2: Download the Model Files

All official files live in the Comfy-Org/Wan_2.2_ComfyUI_Repackaged repository on Hugging Face. You need four file groups:

  • Diffusion models — wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors + low_noise variant (FP8, ~14.3GB each)
  • Text encoder — umt5_xxl_fp8_e4m3fn_scaled.safetensors
  • VAE — wan_2.1_vae.safetensors (shared across the Wan 2.x family)
  • Optional LoRAs — community relighting, style and motion LoRAs

Step 3: Place Files in the Right Folders

Drop diffusion models into ComfyUI/models/diffusion_models/, the text encoder into ComfyUI/models/text_encoders/, and the VAE into ComfyUI/models/vae/. Restart ComfyUI and the workflow templates will auto-locate them.

Step 4: Recommended Settings

For a first render on a 24GB card: 1280×720 resolution, 81 frames (~5 seconds at 16fps), 30 steps, CFG 5.0. If you hit out-of-memory at the VAE decode stage, drop to 1280×704 or 960×544 before touching anything else.

Low VRAM? Use GGUF Quantized Weights

Community GGUF quants (Q5_K_M ≈ 10.8GB, Q6_K ≈ 12GB) run the 14B experts on 12–16GB cards via the ComfyUI-GGUF custom node. Expect a modest quality trade-off in exchange for fitting in memory.

When to Skip Local and Use the API

Local is free per-video but slow on consumer hardware — expect several minutes per clip plus fiddling time. If you ship content daily, the hosted generator (and the Wan API) is faster per result, needs no VRAM, and always runs the newest model versions. Try the online generator free, or read our VRAM requirements guide if you're still deciding on hardware.

Model Variants at a Glance

ModelSizeModesMin VRAM (approx.)
Wan2.2-TI2V-5B5BT2V + I2V hybrid~8GB
Wan2.2-T2V-A14B (FP8)14B MoEText-to-video~24GB
Wan2.2-I2V-A14B (FP8)14B MoEImage-to-video~24GB
14B experts (GGUF Q5/Q6)14B quantizedT2V / I2V12–16GB

Frequently Asked Questions

Where do I download the Wan 2.2 ComfyUI workflow?

You don't need to download workflows separately — ComfyUI includes native Wan 2.2 templates under Workflow → Browse Templates → Video. Model weights come from the Comfy-Org/Wan_2.2_ComfyUI_Repackaged Hugging Face repo.

Can Wan 2.2 run on an RTX 4090?

Yes — the FP8-scaled 14B experts fit in the 4090's 24GB VRAM at 720p/81 frames. Recommended starting settings: 30 steps, CFG 5.0.

What if I only have 8GB of VRAM?

Use the Wan2.2-TI2V-5B model, which was designed for consumer GPUs and fits in roughly 8GB.

Is Wan 2.2 free for commercial use locally?

Yes — the weights are Apache 2.0 licensed, so local generation and commercial usage are both free with no strings attached.

Local ComfyUI or online generator — which should I use?

Local wins on per-video cost and privacy; the online generator wins on speed-to-result, zero setup and always-current models. Many creators prototype locally and scale through the API.

More Wan AI Guides & Tools

Put These Prompts to Work

Generate your video online — free to try, watermark-free results.

Open the Generator