Hunyuan Video LoRA Inference

POST/v1/run

Hunyuan Video Lora by Tencent - generate cinematic videos from text descriptions with AI. Create high-quality video content with natural motion, camera control, and optional audio generation.

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 tencent/hunyuan-video-lora.

Default: tencent/hunyuan-video-lora

stringpromptrequired

The prompt to generate the video from.

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<string>resolution

The resolution of the video to generate.

Allowed values: 480p, 580p, 720p

Default: 720p

Optional<integer>seed

The seed to use for generating the video.

Optional<string>num_frames

The number of frames to generate.

Allowed values: 129, 85

Default: 129

Optional<array<object>>loras

The LoRAs to use for the image generation. You can use any number of LoRAs and they will be merged together to generate the final image.

Default:

Optional<boolean>pro_mode

By default, generations are done with 35 steps. Pro mode does 55 steps which results in higher quality videos but will take more time and cost 2x more billing units.

Default: false

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: text-to-video

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": "tencent/hunyuan-video-lora",
  "prompt": "A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. She wears a black leather jacket, a long red dress, and black boots, and carries a black purse.",
  "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"

Response202 Accepted

{
  "id": "run_abc123",
  "model": "tencent/hunyuan-video-lora",
  "status": "running",
  "outputs": []
}