ComfyUI Tutorial Series Ep 36: WAN 2.1 Installation – Turn Text & Images into Video!

Описание: In this episode, we go through the step-by-step process of setting up the WAN 2.1 model in ComfyUI, allowing you to create videos from both text and images—right on your own computer! 🚀

We’ll start by updating ComfyUI, installing the necessary nodes, and setting up the required models. You’ll also get a clear breakdown of how different versions of the WAN model impact video quality, speed, and compatibility with your hardware. Whether you're working with 1.3B, 14B, or GGUF models, this guide will help you find the best fit for your workflow. 🔧

Additionally, we explore frame rate settings, video length calculations, and how to fine-tune prompts for optimal results. By the end, you’ll have everything you need to generate smooth AI-driven animations with ComfyUI! 🎬

Don’t forget to grab the free workflows on Discord and join the conversation with other creators. Let’s bring your AI video ideas to life! ✨

Get the workflows and instructions from discord for free
  / discord  

Check Other Episodes
   • ComfyUI Tutorial Series: Mastering Stable ...  

---

Test Wan 2.1 Image to Video 14B 480p workflow on RunningHub,
https://www.runninghub.ai/post/189657...

use one of these settings for widht and height
Landscape 16:9 → 832x480px
Portrait 9:16 → 480x832px
Square 1:1 → 640x640px

Add a text prompt in the positive prompt node

For 16 FPS:

Duration → Length Value (in the Latent Video Node)
1 second → 17 frames
2 seconds → 33 frames
3 seconds → 49 frames
4 seconds → 65 frames
5 seconds → 81 frames

---
Unlock exclusive perks by joining our channel:
   / @pixaroma  
--
Comfy Blog Post for Wan 2.1
https://blog.comfy.org/p/wan21-video-...
---
Update ComfyUI

Then Install this nodes from Manager if you don't have them already
ComfyUI-GGUF
ComfyUI-VideoHelperSuite
---
Model Links are in the workflows, but here are some of the links
Go to this page and choose a diffusion model:
https://huggingface.co/Comfy-Org/Wan_...
Place in ComfyUI/models/diffusion_models

Or gguf i2v model for 720p https://huggingface.co/city96/Wan2.1-...
Or gguf i2v model for 480p https://huggingface.co/city96/Wan2.1-...


Info about the models:
1.3B models are smaller and work on GPUs with less VRAM.
14B models are much larger and need a high-VRAM GPU.

Download this text encoder model
https://huggingface.co/Comfy-Org/Wan_...
Place in ComfyUI/models/text_encoders

Download this clip model
https://huggingface.co/Comfy-Org/Wan_...
Place in ComfyUI/models/clip_vision

Download this vae model
https://huggingface.co/Comfy-Org/Wan_...
Place in ComfyUI/models/vae

Restart ComfyUI
Load the workflows

#comfyui #imagetovideo #texttovideoaifree