2025-12-12 15:14:52 +08:00
|
|
|
# Image-To-Image
|
2025-12-11 20:06:17 +08:00
|
|
|
|
|
|
|
|
This example edits an input image with `Qwen/Qwen-Image-Edit` using the `image_edit.py` CLI.
|
|
|
|
|
|
|
|
|
|
## Local CLI Usage
|
|
|
|
|
|
|
|
|
|
```bash
|
|
|
|
|
python image_edit.py \
|
|
|
|
|
--image qwen_bear.png \
|
|
|
|
|
--prompt "Let this mascot dance under the moon, surrounded by floating stars and poetic bubbles such as 'Be Kind'" \
|
|
|
|
|
--output output_image_edit.png \
|
|
|
|
|
--num_inference_steps 50 \
|
|
|
|
|
--cfg_scale 4.0
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
Key arguments:
|
2025-12-12 15:14:52 +08:00
|
|
|
|
2025-12-11 20:06:17 +08:00
|
|
|
- `--image`: path to the source image (PNG/JPG, converted to RGB).
|
|
|
|
|
- `--prompt` / `--negative_prompt`: text description (string).
|
|
|
|
|
- `--cfg_scale`: true CFG scale for Qwen-Image-Edit (quality vs. fidelity).
|
|
|
|
|
- `--num_inference_steps`: diffusion sampling steps (more steps = higher quality, slower).
|
|
|
|
|
- `--output`: path to save the generated PNG.
|
