/api/v1/images/generations with model: anime-waifu, optionally steer it with negative_prompt and seed, and collect the image by its img_uuid. Every image costs 0.2 token ($0.004)./api/v1/images/generations with model: anime-waifu, optionally steer it with negative_prompt and seed, and collect the image by its img_uuid. Every image costs 0.2 token ($0.004).
ratio accepts 1:1 (default), 3:4, 2:3, 9:16, 4:3, 3:2 and 16:9. Tall ratios such as 2:3 or 9:16 leave room for full-body poses; 1:1 and 3:4 suit avatar crops.

Up to 2,000 characters in prompt and another 2,000 in negative_prompt for what to keep out of the image. If you omit negative_prompt, a sensible default is applied.

seed defaults to -1 for a random result. Pass a non-negative integer to reproduce a previous generation, then vary only the prompt to make controlled changes to the same character.

Authorization: Bearer <key> from your backend.prompt, and pick a ratio that matches portrait or full-body framing.{"model": "anime-waifu", "prompt": "…", "ratio": "3:4"} to /api/v1/images/generations and store the returned img_uuid.GET /api/v1/jobs/detail or use custom_callback_url; when status is success, download json[0].value within 24 hours.