Character Sheet for Qwen Image 2.1 | ComfyUI workflow, 1 to 3 photos

Character Sheet for Qwen Image 2.1

Give this free ComfyUI workflow one photo of a person. It draws the same person from the front, the side and the back, full body, on one 2048 x 1152 sheet. A detail pass then makes the sheet 3072 x 1728 and sharpens faces and cloth.

You can add up to two more photos, for example a jacket or an outfit. The cover shows it: photo 1 is the person, photo 2 is the jacket, and the sheet shows the person wearing it.

What you need

No custom nodes. Tested on ComfyUI 0.37.4. If a node shows red, update ComfyUI: older builds do not have the Qwen Image 2.1 nodes.

• qwen_image_2.1_int8_convrot.safetensors (7.3 GB) in models/diffusion_models
• qwen3vl_8b_int8_convrot.safetensors (9.4 GB) in models/text_encoders
• qwen_image_2.1_vae_bf16.safetensors (676 MB) in models/vae
• Qwen-Image-2.1-viggle-turbo-4step-lora-r64.safetensors (340 MB) in models/loras

When you open the workflow, ComfyUI offers to download all four into the right folders.

First sheet

1. Drag the workflow onto the ComfyUI canvas.
2. Load your photo in Photo 1.
3. Press Run. The sheet is saved in output/StableYogi.

More than one photo: Photo 2 and Photo 3 start switched off. Click one, press Ctrl+B, and load a picture. Then name it in the prompt: <image2> is Photo 2 and <image3> is Photo 3.

Memory

We ran it with the graphics memory held to 7 GB, two photos and the detail pass on, and it finished. The model files are bigger than an 8 GB card, so plan for 32 GB of system RAM. Out of memory? Set "upscale on / off" to false.

Known limits

The side view sometimes faces the other way from the prompt. Run it again with a new seed.

Licence

Built with Qwen. Qwen Image 2.1 and the Viggle turbo LoRA are for non-commercial use only. Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) 2026 Hangzhou Tongyi Laboratory Technology Co., Ltd.

More free workflows: Community Resources on my portal.