omnihuman-1-5

📝 Model description pending (TODO). Every value on this page comes from the ModelFold catalog, and no technical detail has been invented.

Overview

Field	Value
Model ID	omnihuman-1-5
Family slug	omnihuman-1-5
Modality	Video Generation (video)
Credits	203
Upstream cost	27 / per second
Pricing source	upstream-api — Upstream official pricing (media)
Endpoint	POST /v1/videos/generations

Request example

export API_BASE="https://modelfold.ai/v1"
export MODELFOLD_API_KEY="mf-..."   # 在控制台 API Key 页面创建

curl -X POST "$API_BASE/videos/generations" \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"omnihuman-1-5","image_url":"https://example.com/reference.png","audio_url":"https://example.com/reference.mp3","prompt":"A paper boat drifting down a rainy street.","output_resolution":"1080","pe_fast_mode":false,"seed":-1}'

Required parameters

Required: image_url, audio_url, prompt.

Pass model parameters at the top level; do not wrap them in input. Replace sample media URLs with your own publicly accessible files. The request waits for generation and returns data[].url.

See the complete parameter reference for conditional requirements, limits and alternative input modes.

Related models

• Model overview
• See all 80 video generation models
• omnihuman-1-5/human-identification
• omnihuman-1-5/subject-detection

See also

• API reference