AI Character Consistency API — Keep Characters Consistent

What Is a Character Consistency API?

A character consistency API uses one or more reference images to reproduce the same subject in new scenes, poses, outfits, and camera angles. Image-reference models are useful for character sheets and stills; reference-to-video models carry that identity into motion.

Muapi exposes both families through the same REST submit-and-poll flow. Choose a model by reference-pack size, input modality, price, or whether the output should be an image or a video.

Key Capabilities

Representative Character Consistency Model Comparison

Reference limits, supported modalities, and prices vary by model. Check each model's Playground schema before submitting production requests.

How to Call the Character Consistency API

1. Choose an image or video model. Select a model based on output type, reference-pack size, modality, and budget.
2. Host your references. Upload source images through POST /api/v1/upload_file, or use publicly reachable URLs accepted by the selected endpoint.
3. Send the task-type fields. Call POST /api/v1/{model-slug} with images_list, a prompt, and any model-specific reference or task-type fields.
4. Poll and persist the result. Check GET /api/v1/predictions/{request_id}/result until status is completed, then store the returned image or video.

curl -X POST https://api.muapi.ai/api/v1/seedance-2.5-omni-reference \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "images_list": [
      "https://example.com/character-front.jpg",
      "https://example.com/character-side.jpg"
    ],
    "prompt": "the character walking through a neon-lit city street at night",
    "omni_reference_task_type": "reference",
    "duration": 5,
    "aspect_ratio": "16:9"
  }'

import requests

response = requests.post(
    "https://api.muapi.ai/api/v1/seedance-2.5-omni-reference",
    headers={"x-api-key": "YOUR_API_KEY"},
    json={
        "images_list": [
            "https://example.com/character-front.jpg",
            "https://example.com/character-side.jpg",
        ],
        "prompt": "the character walking through a neon-lit city street at night",
        "omni_reference_task_type": "reference",
        "duration": 5,
        "aspect_ratio": "16:9",
    },
)
request_id = response.json()["request_id"]

result = requests.get(
    f"https://api.muapi.ai/api/v1/predictions/{request_id}/result",
    headers={"x-api-key": "YOUR_API_KEY"},
)
print(result.json())

Frequently Asked Questions