Generate images from text prompts.
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
The image generation model to use.
"qwen-image"
The text prompt describing the image to generate.
"A futuristic city skyline at sunset"
Whether to automatically enhance the prompt before generation.
Whether to prioritize faster generation.
Guidance scale controlling prompt adherence.
Elements you want to avoid in the generated image.
Number of denoising steps used during generation.
Optional random seed for reproducible results.
Disable the safety checker for generation.
Optional input image for image-to-image generation or editing.
Strength of transformation when using an input image.
Optional LoRA weights identifier.
Scale factor for the primary LoRA weights.
Additional LoRA weights to apply.
Scale values for additional LoRA weights.
Aspect ratio for the generated image.
"16:9"
Controls image resolution or optimization mode.
"optimize_for_quality"
Desired output image format.
"webp"
Compression quality for the output image.