/api/v1/images/generations with model: muse-image and a prompt, optionally guided by up to 9 reference images in image_list. Every job returns a single WebP image at a flat price per image./api/v1/images/generations with model: muse-image and a prompt, optionally guided by up to 9 reference images in image_list. Every job returns a single WebP image at a flat price per image.
image_list as [{"url": "https://…"}]. Describe in the prompt what to keep from them and what to change, for example keeping a product and placing it in a new scene.
ratio to 1:1, 16:9, 9:16, 4:3, 3:4, 3:2 or 2:3. The default auto means 1:1 for text to image and follows the reference images when image_list is given.
muse-image.{"url": "https://…"}. Public JPG, PNG or WebP, up to 30MB each. Large images are downscaled automatically.auto (default), 1:1, 16:9, 9:16, 4:3, 3:4, 3:2 or 2:3.image_size and resolution, and more than 9 reference images. These are rejected before any tokens are charged.image_list does not change the price.POST /api/v1/pricing/quote with model: muse-image to confirm the price for free.Authorization: Bearer <key> from your server.{"model": "muse-image", "prompt": "…"} to /api/v1/images/generations; add image_list and ratio if needed.data.img_uuid and data.cost from the response, then poll GET /api/v1/jobs/detail?img_uuid=<img_uuid> or wait for your callback.POST https://api.goenhance.ai/api/v1/images/generations with model: muse-image.
No. The model picks the output size, so there is no image_size or resolution tier. Use ratio to set the shape.
Up to 9 in image_list. More than 9 is rejected before any tokens are charged.
A single WebP image per job.
0.5 tokens ($0.01) per image, flat. Reference images are not charged.
Poll GET /api/v1/jobs/detail?img_uuid=… or pass custom_callback_url; failed jobs are refunded automatically.