Model Description

This is an upgraded version of the previously released Kontext Reality Transform, trained on the Qwen Image Edit model, yielding better results than the Kontext version! In this version, you can try changing the prompts to modify the scene of the original image; see the recommended prompts for details. Also, don't forget the Chinese language support native to the Qwen Image series.

Recommended Settings

Sampler: Euler

LoRA Weight: 1

CFG: 1.0 (Using Qwen-Image-Lightning-8steps-V1.1, acceleration LoRA weight 1.0)

Steps: 8

Hires Fix recommended: 1.5x upscale, Denoising strength 0.4, Beta scheduler, 8 steps, CFG 1.0, using Qwen-Image-Lightning-8steps-V1.1, acceleration LoRA weight 0.5

Recommended Prompts

Trigger word: transform into realistic photography

Other prompts:

transform into realistic photography, The background is set next to an everyday shopping street.

transform into realistic photography, change the background to a Japanese anime comiket convention, with a sparse crowd of japanese otaku and various japanese male and female cosplayers walking towards various directions in the background.They are wearing various anime costumes from different manga and anime,they are unware of the viewer, the lighting is natural indoor lighting without flashlight

(Use your imagination)

Reposted from Civitai