qwen/qwen-image 🔢🖼️📝✓❓ → 🖼️
About
An image generation foundation model in the Qwen series that achieves significant advances in complex text rendering.
Example Output
Prompt:
"Bookstore window display. A sign displays “New Arrivals This Week”. Below, a shelf tag with the text “Best-Selling Novels Here”. To the side, a colorful poster advertises “Author Meet And Greet on Saturday” with a central portrait of the author. There are four books on the bookshelf, namely “The light between worlds” “When stars are scattered” “The slient patient” “The night circus”"
Output
Performance Metrics
3.47s
Prediction Time
3.48s
Total Time
All Input Parameters
{
"prompt": "Bookstore window display. A sign displays “New Arrivals This Week”. Below, a shelf tag with the text “Best-Selling Novels Here”. To the side, a colorful poster advertises “Author Meet And Greet on Saturday” with a central portrait of the author. There are four books on the bookshelf, namely “The light between worlds” “When stars are scattered” “The slient patient” “The night circus”",
"go_fast": true,
"guidance": 4,
"strength": 0.9,
"image_size": "optimize_for_quality",
"lora_scale": 1,
"aspect_ratio": "16:9",
"output_format": "webp",
"enhance_prompt": false,
"output_quality": 80,
"negative_prompt": " ",
"num_inference_steps": 50
}
Input Parameters
- seed
- Random seed. Set for reproducible generation
- image
- Input image for img2img pipeline
- prompt (required)
- Prompt for generated image
- go_fast
- Run faster predictions with additional optimizations.
- guidance
- Guidance for generated image. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
- strength
- Strength for img2img pipeline
- image_size
- Image size for the generated image
- lora_scale
- Determines how strongly the main LoRA should be applied.
- aspect_ratio
- Aspect ratio for the generated image
- lora_weights
- Load LoRA weights. Only works with text to image pipeline. Supports arbitrary .safetensors URLs, tar files, and zip files from the Internet (for example, 'https://huggingface.co/flymy-ai/qwen-image-lora/resolve/main/pytorch_lora_weights.safetensors', 'https://example.com/lora_weights.tar.gz', or 'https://example.com/lora_weights.zip')
- output_format
- Format of the output images
- enhance_prompt
- Enhance the prompt with positive magic.
- output_quality
- Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
- negative_prompt
- Negative prompt for generated image
- extra_lora_scale
- Scales for additional LoRAs as an array of numbers (e.g., 0.5, 0.7). Must match the number of weights in extra_lora_weights.
- replicate_weights
- Load LoRA weights from Replicate training. Only works with text to image pipeline. Supports arbitrary .safetensors URLs, tar files, and zip files from the Internet.
- extra_lora_weights
- Additional LoRA weights as an array of URLs. Same formats supported as lora_weights (e.g., ['https://huggingface.co/flymy-ai/qwen-image-lora/resolve/main/pytorch_lora_weights.safetensors', 'https://huggingface.co/flymy-ai/qwen-image-realism-lora/resolve/main/flymy_realism.safetensors'])
- num_inference_steps
- Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster.
- disable_safety_checker
- Disable safety checker for generated images.
Output Schema
Output
Example Execution Logs
Using seed: 141586 Generation took 3.34 seconds Total safe images: 1 out of 1
Version Details
- Version ID
0bba9e70f78437359725e0989ead45ca8b09e6c12a070dfe9a09e6856b43a44d- Version Created
- January 20, 2026