This is a simple and tidy workflow for WAN 2.1 Image 2 Video.
It is balance between aesthetics and practicality, putting everything important and related close together and enabling a static workflow without constant zooming and panning.
It also features 3 LoRA nodes and an optional Upscaling process that can be turned off with one click.
Recommended files
Choose one of the diffusion models from Hugging Face or CivitAI → Place in ComfyUI/models/diffusion_models
umt5_xxl_fp8_e4m3fn_scaled.safetensors → Place in ComfyUI/models/text_encoders
clip_vision_h.safetensors → Place in ComfyUI/models/clip_vision
wan_2.1_vae.safetensors → Place in ComfyUI/models/vae
Description
Hotfix
reverted upscale changes (still slightly rearranged as before)
FAQ
Comments (1)
Thank you so much!
I've been struggling for days with some weird desaturation and corruption issues when I tried to adapt flow's start-end workflow to a simple i2v, and all the other "simple" workflows are just so convoluted with extra dependencies. Then I just run with yours and everything works right. I'm still not really sure why - perhaps the cfg, sampler, negative, teacache, multigpu, sage attention... but now I finally have a baseline.
Edit: Okay, as soon as I go up to 120 frames from 73, everything breaks - what gives?
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.