Qwen-Image is more sensitive to prompts. Conflicting prompts will degrade the image generation quality, so please keep this in mind.

---

To better highlight the characteristics of the LoRA, future LoRA cover sample images will use identical parameters to make comparison easier.

---

When running online, please adjust the CFG scale between 2 and 5. A lower CFG value yields more detail, but lower prompt adherence.

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: Fine Art Nude Photography

Reprinted from: Xingmeng｜Qwen-Image｜Photography Style｜Fine Art Nude Photography