Viduq2 is a Vidu model exposed on the Huzz API with a single Huzz key and one consistent, OpenAI-compatible interface. Capabilities: Image-to-image, Reference-to-video, Image generation, Video generation. It supports streaming responses. Long-running jobs run asynchronously with polling. Call it at https://api.huzz.ai using Authorization: Bearer $HUZZ_API_KEY — no per-provider accounts or SDKs required.
FamilyCapabilitiesStreamingAsyncPricing
ViduImage-to-image, Reference-to-video, Image generation, Video generationYesYesUsage-based

​
Endpoints

MethodPathCapability
POST/api/v3/vidu/viduq2/image-to-imageImage-to-image
POST/api/v3/vidu/viduq2/reference-to-videoReference-to-video
POST/api/v3/vidu/viduq2/text-to-imageImage generation
POST/api/v3/vidu/viduq2/text-to-videoVideo generation

​
Code samples

Authenticate with Authorization: Bearer $HUZZ_API_KEY — get a key at huzz.ai/register. 
curl https://api.huzz.ai/v1/images/generations \
  -H "Authorization: Bearer $HUZZ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "viduq2", "prompt": "A serene mountain lake at dawn"}'
Long-running jobs return a prediction id. See Async predictions for the full submit-and-poll lifecycle.