Wan 2.1 I2V 480p LoRA

Wan 2.1 I2V 480p LoRA

Playground

Generate unlimited 480P AI videos with WAN 2.1 Image-to-Video and custom LoRA support for personalized styles. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

wavespeed-ai/wan-2.1/i2v-480p-lora turns a single input image into a short, coherent video clip at 480p, with optional LoRA effects for stylized motion, transformations, or consistent visual “behavior” across runs.

What it’s good at

• Image-to-video animation from one still image (great for product shots, portraits, scenes)
• LoRA-driven motion/effects (for example: rotate, zoom-call framing, playful VFX-style transformations)
• Fast iteration for storyboard-style testing at a lightweight resolution

Inputs

• Prompt (required): describe the action, camera, and mood

• Image (required): the starting frame

• Negative prompt (optional): reduce artifacts or unwanted styles

• LoRAs (optional): add one or more LoRAs with:

• Path: LoRA identifier

• Scale: LoRA strength

• Size: 480p

• Duration: 5s or 10s

• Num inference steps: higher can improve detail/coherence (slower)

• Guidance scale: higher follows the prompt more strictly

• Flow shift: controls motion feel (lower is calmer, higher is more dynamic)

• Seed: set for repeatable results

How to use (Playground)

1. Upload your image.
2. Write a prompt that includes subject + action + camera movement + environment.
3. (Optional) Add a LoRA and start with a moderate scale, then adjust upward only if the effect is too subtle.
4. Keep guidance scale moderate for natural motion; increase it if the model ignores your requested action.
5. Run at 5s first, then move to 10s once the motion looks right.

Prompting tips (I2V)

• Start with a single clear action: walks, turns, smiles, waves, looks back, picks up an object.
• Add camera direction in plain film language: slow push-in, handheld, dolly left, tilt up, rack focus.
• If you use an “effect” LoRA (like deflate/rotate), describe the target as a non-graphic, clearly fictional or toy-like transformation to avoid unwanted safety filtering.

Example prompt style (safe wording): A beach photo becomes a playful VFX shot: the character turns into an inflatable toy version of itself and slowly deflates like a balloon, then settles gently on the sand. Smooth camera push-in, soft sunlight, natural motion, no distortion.

Use cases

• Social content and short ads: animate a key visual into a 5–10s loopable clip
• Product hero animation: subtle parallax, gentle rotation, light camera push for ecommerce
• Stylized LoRA effects: rotate, “video call” framing, playful toon-like transformations
• Prototype storytelling: turn concept art into quick motion beats for pitches

Pricing

Notes

• 480p is ideal for fast iteration, previews, and high-volume generation.
• LoRA effects can overpower the base motion if scaled too high; increase gradually.
• Safety checks may block certain real-person transformations; using fictional/toy framing typically works better.

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",
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "size": "832*480",
  "num_inference_steps": 30,
  "duration": 5,
  "guidance_scale": 5,
  "flow_shift": 3,
  "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-2.1/i2v-480p-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