Qwen-Image is more sensitive to prompts. If there are conflicting prompts, it will reduce the quality of image generation, so please keep this in mind.

---

To better showcase the characteristics of the LoRA, subsequent LoRA cover sample images will maintain completely identical parameters to make it easy for everyone to compare.

---

When running online, please adjust the CFG scale to between 2 and 5. The lower the CFG value, the more details you get, but prompt adherence will be lower.

When running locally, you can consider using the distilled acceleration model for Qwen-Image. Below are the resource links:

1. Accelerated Workflow (4 Steps): https://www.liblib.art/modelinfo/6fbc9a0d81394360812307cc59f4ac44

2. Qwen-Image Distilled Acceleration Model: https://www.liblib.art/modelinfo/cfe5c999b01f4e0ca3531819217c8d71

---

Current LoRA style: Real-Scene Comic

Reprinted from: Xingmeng | Qwen-Image | Photography Style | Real-Scene Comic