Directions
Here’s version 2 of my V2V WAN 2.2 + VACE workflow. Here’s how it works at a high level
Upload subject reference (Node Name: ⭐️ Load Image of Reference Subject)
Upload video reference (Node Name: ⭐️ Media Selection (Reference Video)
Enter Prompt
Enter Manually in WanVideo TextEncode (Default)
Use SwissArmyKnife LLM nodes
Requires additional setup if using Qwen3-VL via LLM Studio (locally hosted model)
Requires API key if using Gemini API
Run Workflow
Notes
Subject/Character
Use a high quality subject reference image
Closeups work best from my testing
The background of your subject reference will influence your video output slightly
I haven’t figured exactly how to properly mask just the subject in a way that works with WAN VACE
Your subject’s identity will not be preserved perfectly due to the nature of VACE and other variables like seed
Best best is to use a subject/character lora is you need it to be consistent
You can turn down the fun reward lora strength if your generated video is too “shiny”
Lora Additions
You can add more loras to fine tune the generated video but try not to add too many because you end up having loras fighting each other and you will get a burned out looking generation
Prompting
Subject: Describe your main subject with clarity — who or what it is, what they’re doing, and how they appear.
Clothing: Focus on what the subject is wearing or how the outfit contributes to mood, texture, colour or story. Consider description of fabrics, accessories, era, and fit.
Movement: Elaborate on how the subject moves, how the camera moves, or any dynamic elements in the scene. Use cinematic language when helpful.
Scene: Define the environment: time of day, location, background/foreground elements, mood, composition and lighting.
Visual Style: Establish the look and feel: lighting, colour-grading, lens effects, film stock, level of realism vs stylised, any elements you don’t want (negative prompt awareness).
I have added prompt examples to the markdown file in the zip
NSFW
This works with NSFW assuming you have a NSFW lora + good prompt. I haven’t found a great high quality nsfw lora so that’s why it’s not included
Major changes from V1
Added image upload for subject reference
Fixed node mismatches with SwissArmyKnife custom nodes
Switched from Gemini to Qwen3 VL (running locally and exposes via Swiss Army Knife nodes)
Added a path to input prompt instead of relying on SwissArmyKnife LLM nodes
Overhauled & Simplified VACE Encoding nodes, now it just uses the subject reference and depth map
Roadmap
Figure how to mask character so subject’s identity is preserved better and the background of the reference image doesn’t influence the generated video too much
Need a better solution for upscaling and interpolation
Explore VACE’s First Frame Last Frame capabilities to generate longer videos
Dial in settings for NSFW loras
Model links
You can find all the models on Huggingface. I am running a Nvidia 3090TI w 24GB VRAM & 128 GB DDR4 RAM. The FP8_e5m2 work best for the 3000 series generation. Generations take about 300-500 seconds on my system
Diffusion model
WAN 2.2 T2V
Text encoder
VAE
LoRAs
High Noise
Low Noise
Model Storage Location
📂 ComfyUI/
├── 📂 models/
│ ├── 📂 diffusion_models/
│ │ ├── Wan2_2-T2V-A14B-HIGH_fp8_e5m2_scaled_KJ.safetensors
│ │ ├── Wan2_2-T2V-A14B-LOW_fp8_e5m2_scaled_KJ.safetensors
│ │ ├── Wan2_2_Fun_VACE_module_A14B_HIGH_fp8_e5m2_scaled_KJ.safetensors
│ │ └── Wan2_2_Fun_VACE_module_A14B_LOW_fp8_e5m2_scaled_KJ.safetensors
│ ├── 📂 vae/
│ │ └── Wan2.1_VAE.safetensors
│ ├── 📂 text_encoders/
│ │ └── umt5_xxl_fp16.safetensors
│ └── 📂 loras/
│ ├── Wan22_A14B_T2V_LOW_Lightning_4steps_lora_250928_rank64_fp16.safetensors
│ ├── Wan2.2-Fun-A14B-InP-HIGH-MPS_resized_dynamic_avg_rank_21_bf16.safetensors
│ ├── Wan2.2-Fun-A14B-InP-LOW-MPS_resized_dynamic_avg_rank_22_bf16.safetensors
│ ├── Instagirlv2.5-HIGH.safetensors
│ └── Instagirlv2.5-LOW.safetensors
Custom Nodes
ComfyUI-WanVideoWrapper - nightly
comfyui_controlnet_aux - v1.1.2
ComfyUI-Easy-Use - v1.3.4
ComfyUI-KJNodes - v1.1.7
ComfyUI-VideoHelperSuite - v1.7.7
ComfyUI-Frame-Interpolation - v.1.0.7
ComfyUI Video Depth Anything - nightly
CRT-Nodes - v1.8.2
Swiss Army Knife - v2.9.1
ComfyUI
ComfyUI - v0.3.65
ComfyUI_frontend - v1.27.10
Python - v3.12.3
Pytorch - 2.9.0+cu128
Description
Initial release
FAQ
Comments (8)
so this is animate wan?
Not tryna be to be a dick but did you read anything in this post? Title, description, literally says wan vace in the thumbnail
yes
Any chance of getting this running with 12GB VRAM at all? Nothing I'm doing is working at all
what step are you getting OOM on? the WanVideoWrapper supports GGUF models so you can try replacing the models with those smaller GGUF
@sukuna126853 It's at the first sampler stage, trying GGUFs but doesn't seem to be working
@LamboBro Try showing the error code from the console. Gemeni can confuse you, but it can also help. It's helped me a lot.
I always get the error that "GeminiUtilMediaDescribe" is missing