Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
ComfyUi 0.3.29 positive node fix,
Runtime profile
Source description
✨ WAN2.1 — Image to video — Simple Workflow
A clean, all-in-one WAN image-to-video workflow built entirely with the UmeAiRT Toolkit for ComfyUI. Only 12 nodes . No spaghetti wires. Just load your model, write your prompt, and hit generate.
⚠️ IMPORTANT — Nodes 2.0 Required
This workflow is built for the Nodes 2.0 (Vue) interface of ComfyUI. If you don't enable it, the workflow may have display problems.
How to activate Nodes 2.0:
Open ComfyUI
Go to Settings (⚙️ icon, bottom-left)
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Use this ComfyUI workflow with Wan Video to turn an input image and written prompt into video; it also supports text-to-video, optional SeedVR2 tiled upscaling, and saving generated images with all generation parameters.
Choose the auto or manual setup path: the auto version lists automatic model downloads, while manual setup lists model files and their ComfyUI folders.
Manual setup lists an image and written prompt, plus an I2V model, CLIP, CLIP-VISION, VAE, Speed LoRA, and an upscaling model.
The base option lists 480p or 720p I2V models; GGUF options list Q8, Q5, or Q3 at 480p or 720p.
Generated images can retain all generation parameters for online publishing and remixing.
Before loading it, turn on “Use Nodes V2 (Vue)” in ComfyUI Settings and refresh the page.
Suggestion · not verified
Install ComfyUI-UmeAiRT-Toolkit through ComfyUI Manager by searching “UmeAiRT,” or use the UmeAiRT Auto-Installer.
Suggestion · not verified
Named node packs include: comfyui-custom-scripts, comfyui-easy-use, comfyui-florence2, comfyui-frame-interpolation, comfyui-impact-pack, comfyui-kjnodes, comfyui-multigpu, comfyui-mxtoolkit, comfyui-videohelpersuite, ComfyUI-Upscaler-Tensorrt, rgthree-comfy, and was-node-suite.-S
Named model items include: clip_vision_h.safetensors, umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors, wan2.1_i2v_480p_14B_bf16.safetensors, wan2.1-i2v-14b-480p-Q5_K_M.gguf, rife47.pth, and MiaoshouAI/Florence-2-base-PromptGen-v2.0.
ComfyUI-UmeAiRT-Toolkit is listed as the custom node, with the upscaler, face detailer, and metadata saver packaged internally; no other custom nodes are listed as needed.
Toggle the built-in SeedVR2 tiled upscaler on or off; the description notes that it is slower than a classic upscaler and offers significantly better quality.
Use three LoRA slots with individual on/off toggles and strength controls; additional LoRA modules can be connected.
The package list names additional node packs, but it does not show which ones this workflow needs; verify the required packages before running.
Suggestion · not verified
No license is listed; check the applicable usage terms before publishing.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
2 excerptsSource context: 101452 downloads · Type Workflows · Base model Wan Video
Find "Use Nodes V2 (Vue)" and toggle it ON
Refresh the page
Load the workflow
If you prefer the classic interface, check out my Legacy version of this workflow instead ( link ).
🎯 Features
Text-to-video generation
Automatic download of models in auto version
Built-in SeedVR2 upscaler — high-quality tiled upscaling (toggleable on/off) Slower than a classic upscaler, but significantly better quality
Full metadata embedding — your images are saved with all generation parameters, ready for online publishing and remixing
3 LoRA slots — with individual on/off toggles and strength control and you can connect as many other lora modules to each other for as many LoRA as you want.
📦 Custom Node Required
Only one custom node to install:
👉 ComfyUI-UmeAiRT-Toolkit
Install via ComfyUI Manager (search "UmeAiRT") or use the UmeAiRT Auto-Installer . The Toolkit packages everything internally — upscaler, face detailer, metadata saver. No other custom nodes needed.
📂 Files you need (in manual version)
For base version I2V Model : 480p or 720p In models/diffusion_models
For GGUF version I2V Quant Model :
Common files : CLIP: umt5_xxl_fp8_e4m3fn_scaled.safetensors in models/clip CLIP-VISION: clip_vision_h.safetensors in models/clip_vision VAE: wan_2.1_vae.safetensors in models/vae Speed LoRA: 480p , 720p in models/loras
ANY upscale model:
Realistic : RealESRGAN_x4plus.pth
Anime : RealESRGAN_x4plus_anime_6B.pth
in models/upscale_models
Estimated VRAM requirement
Estimate unavailable
38.2 GB across 4 of 6 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
Requirements
18 requirementsVision model · 1.18 GB · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
MiaoshouAI/Florence-2-base-PromptGen-v2.0
File unverifiedVision model · Hugging Face · MiaoshouAI/Florence-2-base-PromptGen-v2.0 · Florence 2 Base PromptGen v2.0
Checkpoint · Hugging Face
Text encoder · 6.27 GB · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
VAE · 242 MB · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
Checkpoint · 30.5 GB · SAFETENSORS · Hugging Face · dx158/wan_2.1_comfyui_repackaged
Node pack · Registry
Node pack · Registry
comfyui-florence2
Source context: 100949 downloads · Type Workflows · Base model Wan Video
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
was-node-suite-comfyui
PossibleNode pack · Registry
