Wan 2.2 T2V 5b 720p LoRA API Documentation

Wan 2.2 T2V 5b 720p LoRA API Documentation

Playground

Wan 2.2 T2V 5B is a 5B text-to-video model with LoRA support that generates 720p videos from text prompts for easy personalization. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Wan 2.2 T2V 5B is a 5B-parameter text-to-video model with LoRA support that generates 5-second, 1280×720 videos from text prompts. It is built on WAN AI’s Mixture of Experts (MoE) architecture, combining high-noise and low-noise experts across denoising timesteps for sharp details, smooth motion, and strong cinematic style.

Why it looks great

• Cinematic-level aesthetic control Tuned to professional filmmaking standards, with rich control over lighting, color palette, composition, lens, and camera movement.
• Large-scale complex motion Handles dramatic actions, character interactions, and challenging camera paths while keeping motion stable and natural.
• Precise semantic compliance Strong scene understanding and multi-object generation, so shots stay close to your story beats and prompt.
• 5B parameter backbone Higher texture fidelity, better character consistency, and improved temporal coherence across frames.

Pricing

• Flat price: $0.10 per run

How to Use

1. In the prompt box, describe the scene, characters, motion, camera, lighting, and style in detail.
2. (Optional) Click Add Item under loras to attach up to 3 LoRA adapters.

• In each LoRA slot, paste the LoRA path (owner/model-name) or a direct .safetensors URL.
• Use the scale slider to control strength (for example, 0.6–1.0 for most character or style LoRAs).

3. Choose the size 1280×720 or 720×1280.
4. Set the seed
5. Click Run. After generation finishes, preview the video on the right panel and download it if you are satisfied.

LoRA Guides

• How to train your LoRA?
• How to use your LoRA?

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "size": "1280*720",
  "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/t2v-5b-720p-lora" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters