qwen/qwen-image-2512
Qwen Image 2512 is an improved version of Qwen Image with more realistic human generation, finer textures, and stronger text rendering
Capabilities
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
prompt* | string | Text prompt for image generation. | — | — |
aspect_ratio | string | Aspect ratio for the generated image. | "16:9" | 1:116:99:164:33:43:22:3custom |
disable_safety_checker | boolean | Disable safety checker for generated images. | false | — |
go_fast | boolean | Use the model with additional optimizations for faster generation. | true | — |
guidance | number | Guidance for generated image. Use higher values for stronger prompt adherence. | 4 | min: 0, max: 10 |
height | integer | Height of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16. | — | min: 256, max: 2048 |
image | string(uri) | Input image for image2image generation. The aspect ratio of your output will match this image. | — | — |
negative_prompt | string | Negative prompt for image generation. | " " | — |
num_inference_steps | integer | Number of denoising steps. Use less steps for faster generation. | 40 | min: 20, max: 50 |
output_format | string | Format of the output images. | "webp" | webpjpgpng |
output_quality | integer | Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs. | 95 | min: 0, max: 100 |
seed | integer | Random seed. Set for reproducible generation. | — | — |
strength | number | Strength for image2image generation. 1.0 corresponds to full destruction of information in image. | 0.8 | min: 0, max: 1 |
width | integer | Width of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16. | — | min: 256, max: 2048 |
promptrequiredstringText prompt for image generation.
aspect_ratiostringAspect ratio for the generated image.
"16:9"disable_safety_checkerbooleanDisable safety checker for generated images.
falsego_fastbooleanUse the model with additional optimizations for faster generation.
trueguidancenumberGuidance for generated image. Use higher values for stronger prompt adherence.
4min: 0, max: 10heightintegerHeight of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16.
imagestringInput image for image2image generation. The aspect ratio of your output will match this image.
negative_promptstringNegative prompt for image generation.
" "num_inference_stepsintegerNumber of denoising steps. Use less steps for faster generation.
40min: 20, max: 50output_formatstringFormat of the output images.
"webp"output_qualityintegerQuality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs.
95min: 0, max: 100seedintegerRandom seed. Set for reproducible generation.
strengthnumberStrength for image2image generation. 1.0 corresponds to full destruction of information in image.
0.8min: 0, max: 1widthintegerWidth of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16.
47c060e80055Updated: 7/25/2026137.1K runs
cinemasetfree.com