VNCCS Pose Studio is a professional 3D posing, framing, lighting, and pose-library environment running directly inside a ComfyUI node. It is designed for building high-quality pose/control references without leaving the graph: adjust the character body, pose bones interactively, frame the camera, tune lights, manage saved poses, and output single images or pose batches.
Second version of Pose Studio lora for Qwen Image 2.1 is here!
Fixes:
Fingers on anime characters no longer distorted.
Added lights control system. Can still be not precise as in Pose Studio, but should work in most scenarios.
More control to head position.
https://huggingface.co/MIUProject/VNCCS_PoseStudio_QI2.1/tree/main
You must install https://github.com/AHEKOT/ComfyUI_VNCCS_Utils node pack to use this LoRA
Description
Second version of Pose Studio lora for Qwen Image 2.1 is here!
Fixes:
Fingers on anime characters no longer distorted.
Added lights control system. Can still be not precise as in Pose Studio, but should work in most scenarios.
More control to head position.
You can download LoRa and workflow from my HF https://huggingface.co/MIUProject/VNCCS_PoseStudio_QI2.1/tree/main
You must install https://github.com/AHEKOT/ComfyUI_VNCCS_Utils to use this LoRa
FAQ
Comments (9)
!!! Exception during processing !!! Pose Studio frontend sync failed: Live capture timed out; old captures cannot be used.
what version? 0.7.0 is last one.
Pose Studio—why did I only discover it now? What a shame; it really suits me. Thank you for your dedication.
no butt slider?
MakeHuman model don't have default one, and if i add it myself - it would distort model, so no)
And how can I generate at higher res? tried with 4096x4096 in the vnccs node. tried with qwen2.1 (25 steps) and qwen2.1 turbo (8steps) and got artifacts/body horror. also in the text encode qwen 2.1 image node resolution is set by default at 1024. I changed that too but it didn't seem to do anything just prolong the rendering needlessly, at first I did not change res in vnccs node only in qwen 2.1 and the res remained the one mentioned in vnccs.
Why does it look like 3d art even in your demo images? Also with the previous version the results are always flat synthetic looking. Do you have any examples of realistic looking results with instructions to achieve them?
We fed v1.1 photoreal images instead of the mannequin (a pose image and the person, prompt "Draw character from image2") and the results stayed photoreal, pose copied on 5 of 6.
很喜歡您這版，人物體型沒有被強制限制住，可以保持原始體態，這樣讓pose用起來變得超實用的。