Wan 2.1 V2V 720p LoRA API Documentation

Wan 2.1 V2V 720p LoRA API Documentation

Playground

Wan 2.1 V2V 720P LoRA converts source videos into 720P AI-enhanced video-to-video edits with support for custom LoRA personalization. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Wan 2.1 Video-to-Video 720p LoRA is a powerful video transformation model that converts existing videos into new styles, aesthetics, or visual treatments. With full LoRA support, apply custom styles, artistic effects, or consistent character appearances to transform your footage.

Why It Stands Out

• Video-to-video transformation: Convert existing videos into different styles while preserving motion.
• LoRA support: Apply up to 3 custom LoRA models for specific styles, characters, or aesthetics.
• Prompt-guided transformation: Describe the visual style you want to achieve.
• Prompt Enhancer: Built-in AI-powered prompt optimization for better results.
• Negative prompt support: Exclude unwanted elements for cleaner outputs.
• Fine-tuned control: Adjust strength, guidance scale, and flow shift for precise results.
• Reproducibility: Use the seed parameter to recreate exact results.

Parameters

How to Use

1. Upload your source video — drag and drop a file or paste a public URL.
2. Write a prompt describing the visual style you want. Use the Prompt Enhancer for AI-assisted optimization.
3. Add LoRAs (optional) — select up to 3 LoRA models and adjust their scale.
4. Add a negative prompt (optional) — specify elements to exclude.
5. Adjust parameters — set strength, guidance scale, and other settings as needed.
6. Click Run and wait for your video to generate.
7. Preview and download the result.

How to Use LoRA

LoRA (Low-Rank Adaptation) lets you apply custom styles without retraining the full model.

• Add LoRA: Enter the LoRA path and adjust the scale (0.0–1.0).
• Multiple LoRAs: Combine up to 3 LoRAs for layered effects.
• Recommended LoRAs: Check the interface for suggested LoRAs with preview images.

Best Use Cases

• Style Transfer — Convert videos to anime, cartoon, cinematic, or artistic styles.
• Visual Effects — Apply consistent effects like flat color, watercolor, or sketch styles.
• Content Repurposing — Transform footage into different visual aesthetics.
• Brand Consistency — Apply branded visual styles across multiple videos.
• Creative Projects — Experiment with unique visual treatments.

Pricing

Pro Tips for Best Quality

• Use lower strength (0.5–0.7) to preserve more of the original video.
• Use higher strength (0.8–0.95) for more dramatic style transformations.
• Start with one LoRA and add more gradually to understand their combined effect.
• Adjust LoRA scale based on how strongly you want the style applied.
• Use negative prompts to reduce artifacts like blur, distortion, or unwanted elements.
• Fix the seed when iterating to compare different parameter settings.

Notes

• Maximum of 3 LoRAs per generation.
• Ensure uploaded video URLs are publicly accessible.
• Processing time varies based on duration and current queue load.
• Please ensure your content complies with usage guidelines.

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",
  "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
  "num_inference_steps": 30,
  "duration": 5,
  "strength": 0.9,
  "guidance_scale": 5,
  "flow_shift": 3
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/v2v-720p-lora" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters