Wan2.2 Start Frame – End Frame Workflow (ComfyUI)
Create stunning, controllable AI videos using the Wan2.2 model with start and end frame control. This workflow is especially powerful when combined with consistent character LoRA’s, allowing you to animate your custom AI characters smoothly.
✅ What this workflow does
Allows you to define a start and end frame for better motion control
Determine FPS (I advise 24fps or 30fps for this workflow)
Works perfectly with character LoRA's for realistic results, like my character LoRA's
I use this setup on an RTX 4090 and can render a 5-second video in under 150 seconds.
⚠️ Before You Start
If you're new to ComfyUI or haven’t installed the Comfy Manager, I highly recommend starting with my Photorealistic ComfyUI workflow guide first. It covers the basics of installation and file setup. You can find it linked in my Discord or bio.
🧠 Required Models & Files
Diffusion Models (choose based on noise level)
📁 Place these in:C:\Users\your-name\Stability Matrix\Data\Packages\ComfyUI\models\diffusion_models
LoRA Models (not needed for V2, see "About this version")
📁 Place these in:C:\Users\your-name\Stability Matrix\Data\Packages\ComfyUI\models\loras
VAE
📁 Place in:C:\Users\your-name\Stability Matrix\Data\Packages\ComfyUI\models\vae
Clip
📁 Place in:C:\Users\your-name\Stability Matrix\Data\Models\TextEncoders
Final check
Make sure your ComfyUI is updated to the latest version if you get any error messages after installing everything.
🤖 Make your own Character LoRA
Want to learn how to make consistent Character LoRAs from scratch?
Join my private Discord:
https://huslyo123.carrd.co/
🙏 Credit where credit is due
This workflow is a remix of several brilliant community contributions, including:
✨ Want to create consistent character models, explore A1111 workflows, and get exclusive guides & tips? -> https://www.fanvue.com/huslyo123/fv-3
Curious what’s included? Full overview here → https://huslyo123.carrd.co/
Description
If you like this workflow and guide, leave a thumbs up on this page. It really helps a lot!
Some users had issues getting smooth motion. In this version I’ve switched to lightx2v_I2V_14B_480p instead of the model used in V1. It might help with that.
Just leave the disabled node as-is!
👉 Download the new model and place it in your LoRA folder:
https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank32_bf16.safetensors
FAQ
Comments (15)
This flow is fantastic. Thank you very much, Huslyo123, for your work.
Run this.. and just get blurry transitions, i am not having luck with WAN2.2 at all.. so weird
Did you ever figure this out? I'm having the same issue.
Don't give up I can run it on a RTX 3060 with 12 GB Vram
@wiikid3000234 I think i actually had something to do with my comfyui, like a remove and reinstall. or i just moved to a new one, so many out there for wan
@BrownRecluse666 YEP.. amazing..
have the same problem. I have the newest ComfyUI and a RTX 4080 with 12 G VRAM
simple and straight to the point thank you !
it works, but its getting blurry between the image refs. I tried disabling the lightning lora, i changed from lcm to euler. I'm also on a 4090. next i will try to increase steps. and tweaking with it - any idea on why it's happening?
doesnt work. I keep getting a blurry transition
Thank you, I appreciate the directions and links to the required files. I wish everyone was as organized. Worked for me on my first try. Takes about 235 seconds on a RTX 5060 TI 16 GB VRAM
Hi! I'm pretty new to video generation. I'm taking a look at your workflow and so far it is clear to me, but I'm struggling with the use of character LORAs. I saw yours and noticed that they're based on ZImage and SDXL... do they actually work with this workflow that is using WAN i2v as base? Where do I add the LORA loading node in your workflow? Do I use the regular "Load LORA" node or a "Power Lora Loader (rgthree)" one? I hope you can give me an insight on this, thank you!
Hi! You can only use a character LoRA on the model their trained on. A Z-Image Turbo LoRA will not work in an SDXL workflow etc. If you want to have a character LoRa for this workflow, you should make / search for a Wan2.2 LoRA.
i was getting the fading bird instead of flying and my problem was i had my lora in a different folder and the program didnt throw an error. reading back through the cmd window i found it didnt see it and was skipping it. once i pointed it to the lightx2v file it works perfectly
So far its the only one that has worked for First Last frame so thank you, my issue seems to be the starter image is massively cropped