MOSS Layout from Qwen-VL

ComfyUI-MOSS-QwenVL-Layout

A ComfyUI node that turns a reference image into a MOSS-Image layout prompt. Qwen3-VL / Qwen3.5-VL looks at your image, finds the things you ask for (including text, if you ask), and the node writes the layout JSON that MOSS-Image expects: captions, text content and bounding boxes converted to MOSS's abs_centralized / yxyx coordinate format.

You can also add change requests ("make the dress red", "replace the man with an elderly woman in a grey coat", "add a dog on the left"). The captions are then written to describe the edited result, so MOSS generates the changed version while keeping the original composition.

Unofficial community node. Not affiliated with the MOSS-Image team or Alibaba/Qwen.

Install

Manual

cd ComfyUI/custom_nodes
git clone https://github.com/leroy989/ComfyUI-MOSS-QwenVL-Layout
pip install -r ComfyUI-MOSS-QwenVL-Layout/requirements.txt   # only needed for the hf_model path

Restart ComfyUI. The node is at Add Node → MOSS-Image → MOSS Layout from Qwen-VL.

Usage

1. Connect an IMAGE.
2. Set width / height to your MOSS output size (0 = use the image's size). Values are rounded to multiples of 16, as MOSS requires.
3. List what to detect in targets, one per line. Text is only detected when you ask for it (for example title text, the sign).
4. Optionally fill in change_request, one change per line.
5. Connect the prompt output to your MOSS-Image text prompt.
6. Use the preview output to check the boxes before generating.

Choosing a Qwen backend

| Backend | How | Notes | |---|---|---| | CLIP input | Load Qwen3-VL / Qwen3.5-VL as a text encoder and connect it to clip | Uses ComfyUI's text generation. Needs a recent ComfyUI. Less tested, so check raw_qwen_output on first use. | | hf_model | Leave clip empty and set hf_model to a Hugging Face repo or local folder | Uses transformers>=4.57. Most dependable. Turn keep_loaded off to free VRAM before MOSS runs. |

Inputs

| Input | Description | |---|---| | image | Reference image | | width, height | Target MOSS canvas (0 = use image size), rounded to multiples of 16 | | targets | Things to detect, one per line | | meta | Comma-separated style/meta tags for summary.meta (e.g. poster, photo). This is the only place style comes from: Qwen is told not to describe art style or medium in any caption | | coord_mode | normalized_0_1000 (Qwen3-VL / 3.5) or absolute_pixels (Qwen2.5-VL style) | | max_new_tokens, temperature, seed | Generation settings | | clip (optional) | Qwen VL text encoder | | hf_model, keep_loaded (optional) | Standalone Hugging Face path | | change_request (optional) | Edits to apply, one per line |

Outputs

| Output | Description | |---|---| | prompt | MOSS layout JSON | | preview | Image with the converted boxes drawn on it | | raw_qwen_output | Unprocessed model response, for debugging | | width, height | Final rounded canvas size |

Change request tips

• Describe replacements in concrete visual terms: "elderly woman, grey wool coat, short white hair" works better than "a different person".
• Boxes follow the reference image. For objects you add, Qwen guesses the position, so adjust the bbox values by hand if needed.
• Global changes ("golden hour lighting", "winter") are applied to the overall caption and affected items.

How the coordinates work

MOSS layouts use absolute pixel boxes ordered [y_min, x_min, y_max, x_max], with the canvas center as the origin. Qwen3-VL returns [x1, y1, x2, y2] on a 0–1000 grid. The node scales to your canvas size, subtracts W/2 and H/2, and reorders the values. Because the 0–1000 grid is size-independent, the layout still maps correctly if your target canvas has a different aspect ratio from the reference image (the layout is stretched to fit).

Credits and licenses

This repo contains no model weights. Please read the license terms of the models you use:

• MOSS-Image (see its model page and user guide for the layout format)
• Qwen3-VL / Qwen3.5-VL (Qwen team)

Code in this repo is MIT licensed.