Skip to content

Conversation

qinxuye
Copy link
Contributor

@qinxuye qinxuye commented Aug 5, 2025

企业微信20250805-205023@2x 282a601545b21155b9bd9368a47ea74d

Magic prompt suffix is important:

"en": "Ultra HD, 4K, cinematic composition.", # for english prompt
"zh": "超清,4K,电影级构图" # for chinese prompt

Params:

Prompt: A coffee shop entrance features a chalkboard sign reading "Qwen Coffee 😊 $2 per cup," with a neon light beside it displaying "通义千问". Next to it hangs a poster showing a beautiful Chinese woman, and beneath the poster is written "π≈3.1415926-53589793-23846264-33832795-02384197". Ultra HD, 4K, cinematic composition

Negative Prompt: text, watermark, copyright, blurry, low resolution

width: 1664

height: 928

Remember to set quantize_text_encoder: None when running on large GPU memory device.

@XprobeBot XprobeBot added this to the v1.x milestone Aug 5, 2025
@qinxuye qinxuye changed the title FEAT: Qwen-Image FEAT: [model] Qwen-Image Aug 5, 2025
Copy link
Contributor

@amumu96 amumu96 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@XprobeBot XprobeBot added the gpu label Aug 6, 2025
@qinxuye qinxuye merged commit f2db1c8 into xorbitsai:main Aug 6, 2025
10 of 13 checks passed
@qinxuye qinxuye deleted the feat/qwen-image branch August 6, 2025 08:13
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants