← All models
Qwen Image open source model - fast, highly capable image generation model from Alibaba Qwen
images
Details
- Accepts
- text + image
Pricing
- Price
- 3.75 cr / image
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | integer | Random seed. Set for reproducible generation |
| image | string | Input image for img2img pipeline |
| promptrequired | string | Prompt for generated image |
| go_fast | boolean | Run faster predictions with additional optimizations. |
| guidance | number | Guidance for generated image. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5 |
| strength | number | Strength for img2img pipeline |
| image_size | —enum: optimize_for_quality, optimize_for_speed | Image size for the generated image |
| lora_scale | number | Determines how strongly the main LoRA should be applied. |
| aspect_ratio | —enum: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2… | Aspect ratio for the generated image |
| lora_weights | string | |
| output_format | —enum: webp, jpg, png | Format of the output images |
| enhance_prompt | boolean | Enhance the prompt with positive magic. |
| 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 |
| negative_prompt | string | Negative prompt for generated image |
| extra_lora_scale | array | 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 | string | |
| extra_lora_weights | array | |
| num_inference_steps | integer | Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster. |
| disable_safety_checker | boolean | Disable safety checker for generated images. |