Dreamstudio Generate Image From Text

Random seed for reproducible generation. Use the same seed with same parameters to get identical results. If omitted, a random seed is used.

Number of diffusion steps. More steps generally improve quality but take longer. Typical range: 30-50. If omitted, engine's default is used.

Width of generated image in pixels. Must be a multiple of 64. Constraints: For 768 engines: 589,824 ≤ height*width ≤ 1,048,576. For other engines: 262,144 ≤ height*width ≤ 1,048,576. If omitted, engine's default width is used.

Height of generated image in pixels. Must be a multiple of 64. Constraints: For 768 engines: 589,824 ≤ height*width ≤ 1,048,576. For other engines: 262,144 ≤ height*width ≤ 1,048,576. If omitted, engine's default height is used.

Available sampler algorithms for image generation.

Number of images to generate in a single request. Default is 1. Higher values consume more API credits.

Classifier-Free Guidance scale - how strictly to follow the text prompt. Higher values (7-15) follow prompt more closely, lower values (1-7) allow more creative freedom. If omitted, engine's default is used.

Engine identifier for generation (e.g., 'stable-diffusion-v1-5', 'stable-diffusion-xl-1024-v1-0'). Use DREAMSTUDIO_LIST_ENGINES to get available engines. Using invalid engine_id will cause the request to fail.

Organization ID to scope the request to. If not provided, uses the user's default organization from their account.

List of text prompts with optional weights. At least one prompt is required.

CLIP guidance presets for text-to-image generation.