---
title: book_flatten_and_crop_qwen_image_edit_2509
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/book_flatten_and_crop_qwen_image_edit_2509"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/book_flatten_and_crop_qwen_image_edit_2509.md"
repository: AI-ModelScope/book_flatten_and_crop_qwen_image_edit_2509
last_updated: 2026-06-17
license: apache-2.0
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Qwen/Qwen-Image-Edit-2509
base_model_relation: adapter
parameters: 92.2M
tensor_type:
  - F32
library_name:
  - lora
  - diffusers
  - safetensors
  - pytorch
frameworks:
  - pytorch
supports_inference: img2img
downloads: 65
stars: 1
tags:
  - image-to-image
  - lora
  - diffusers
  - "template:diffusion-lora"
---

# book_flatten_and_crop_qwen_image_edit_2509

> book_flatten_and_crop_qwen_image_edit_2509 - AI-ModelScope 在 ModelScope 开源的模型。Book Flatten and Crop

AI-ModelScope/book_flatten_and_crop_qwen_image_edit_2509 是 ModelScope 魔搭社区上的 92.2M 参数text-to-image-synthesis模型，采用 apache-2.0 许可，基于 Qwen/Qwen-Image-Edit-2509 构建，并支持在线推理（img2img）。

- **Repository**: AI-ModelScope/book_flatten_and_crop_qwen_image_edit_2509
- **License**: apache-2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 92.2M
- **Base model**: Qwen/Qwen-Image-Edit-2509
- **Online inference**: img2img
- **Tags**: image-to-image, lora, diffusers, template:diffusion-lora
- **Downloads**: 65
- **Stars**: 1
- **Last updated**: 2026-06-17

Source: https://www.modelscope.cn/models/AI-ModelScope/book_flatten_and_crop_qwen_image_edit_2509

---

# Book Flatten and Crop

<Gallery />

## Model description 

Flattens, crops and merges images that are split between 2 pages. User will need to play around with aspect ratio and resolution to get it right (different books have different aspect ratios). Works well with https:&#x2F;&#x2F;huggingface.co&#x2F;Osrivers&#x2F;Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors&#x2F;tree&#x2F;main and https:&#x2F;&#x2F;huggingface.co&#x2F;eigen-ai-labs&#x2F;eigen-banana-qwen-image-edit for speed and color accuracy.

## Trigger words

You should use `flatten and crop the book image` to trigger the image generation.

You should use `remove the middle crease` to trigger the image generation.

You should use `zoom in` to trigger the image generation.


## Download model


[Download](/tarn59/book_flatten_and_crop_qwen_image_edit_2509/tree/main) them in the Files & versions tab.