TOTAL CONTROL! Qwen-powered reposing keeps characters consistent in every action.
Who it's for: creators who want this pipeline in ComfyUI without assembling nodes from scratch. Not for: one-click results with zero tuning - you still choose inputs, prompts, and settings.
Open preloaded workflow on RunComfy
Open preloaded workflow on RunComfy (browser)
Why RunComfy first
- Fewer missing-node surprises - run the graph in a managed environment before you mirror it locally.
- Quick GPU tryout - useful if your local VRAM or install time is the bottleneck.
- Matches the published JSON - the zip follows the same runnable workflow you can open on RunComfy.
When downloading for local ComfyUI makes sense - you want full control over models on disk, batch scripting, or offline runs.
How to use (local ComfyUI)
1. Load inputs (images/video/audio) in the marked loader nodes.
2. Set prompts, resolution, and seeds; start with a short test run.
3. Export from the Save / Write nodes shown in the graph.
Expectations - First run may pull large weights; cloud runs may require a free RunComfy account.
Overview
Repose your character with a Qwen-powered pose workflow. Use VNCCS PoseStudio's 3D editor for precise control. Add a scene prompt to shape the setting. Keep the face, identity, and clothing consistent. Create dance, boxing, or running images. Iterate faster with the dedicated PoseStudio LoRA.
Important nodes:
Reference character
Pose from VNCCS PoseStudio
Scene prompt and style
Sampling and refinement
Export and upscale
Notes
Qwen Image 2.1 VNCCS PoseStudio | 3D PoseStudio Reposing - see RunComfy page for the latest node requirements.
Description
Initial release - Qwen-Image-2.1-VNCCS-PoseStudio.
FAQ
Comments (3)
Thanks working perfectly fine. Can you share a workflow where i can also add another image and it would load the pose from that image. It would be very easy and useful
Do I need to prompt "blonde woman, black haired man, standing proudly" with every new character or there is some universal prompt for Pose studio node?
Is there a guide for prompting?
Also will 2048 resolution and 50 steps give better results, is it problem to change this?
