Ideogram V3 Character Remix API Reference

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to ideogram-ai/ideogram-v3/character/remix.

Default: ideogram-ai/ideogram-v3/character/remix

stringpromptrequired

The prompt to remix the image with

stringimagerequired

The image URL to remix

Optional<array<string>>images

A set of images to use as style references (maximum total size 10MB across all style references). The images should be in JPEG, PNG or WebP format

Optional<number>strength

Strength of the input image in the remix

Range: 0.01 to 1

Default: 0.8

Optional<string>rendering_speed

The rendering speed to use.

Allowed values: TURBO, BALANCED, QUALITY

Default: BALANCED

Optional<array<string>>reference_masks

A set of masks to apply to the character references. Currently only 1 mask is supported, rest will be ignored. (maximum total size 10MB across all character references). The masks should be in JPEG, PNG or WebP format

Optional<array<string>>reference_images

A set of images to use as character references. Currently only 1 image is supported, rest will be ignored. (maximum total size 10MB across all character references). The images should be in JPEG, PNG or WebP format

Optional<string>aspect_ratio

The aspect ratio of the generated image.

Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16

Optional<integer>seed

Seed for the random number generator

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: image-to-image

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async

# 1. Submit a generation request curl -X POST https://api.sandbase.ai/v1/run \ -H "Authorization: Bearer $SANDBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "ideogram-ai/ideogram-v3/character/remix", "prompt": "A glamorous portrait photograph of a woman in an elegant ballroom setting. The subject wears a champagne-colored ball gown with a fitted bodice, long sleeves, and a full skirt adorned with delicate lace appliques. The dress features a crystal-embellished hair accessory and pearl drop earrings. The grand staircase has ornate gold railings and leads to an elaborate crystal chandelier hanging from an arched ceiling. The walls are decorated with classical paintings featuring floral motifs. The lighting is warm and dramatic, creating a soft glow throughout the space. The composition is shot in a formal portrait style with the subject positioned on the lower landing of the staircase, looking over her shoulder at the camera.", "image": "https://static.sandbase.ai/examples/ideogram-ai/ideogram-v3/character/remix/input_image_0.avif", "aspect_ratio": "21:9" }' # 2. If the response is still running, poll the returned id curl https://api.sandbase.ai/v1/run/run_abc123 \ -H "Authorization: Bearer $SANDBASE_API_KEY"