alibaba/wan-2.1-lora/image-to-videoFrom 36 credits per run· Image to Video

Wan 2.1 LoRA image-to-video animates your photo into a 5 or 10 second clip at 480p or 720p with up to three of your own LoRA files, including camera-move LoRAs. The clip keeps the shape of the photo, and nothing is filtered.

Call it with the model name alibaba/wan-2.1-lora/image-to-video on POST /jobs/createTask, from 36 credits per run ($0.36). New accounts get 30 free credits to try it in the Playground first.

  • Create Video
  • Image to Video
  • Edit Video
  • Up to 720p
  • 5–10s clips
  • Loads your own LoRA

Introduction

Wan 2.1 LoRA Image to video animates one photo with up to three of your LoRA files loaded on Alibaba's open 14B video model.

Choose a mode by starting material

What you haveMode
a written descriptionWan 2.1 LoRA Text to video
a photo to animateWan 2.1 LoRA Image to video
a clip to restyleWan 2.1 LoRA Video to video
a still image instead of a clipWan 2.1 Image LoRA Text to image

Key features

Camera and effect LoRAs

Orbit, dolly and other effect LoRAs trained for Wan 2.1 image-to-video load by direct link. In our example an orbit LoRA swung the camera round behind the subject; without it, at the same seed, the camera stayed still.

Repeatable runs

The same seed and inputs gave a byte-identical clip in our test. That makes this endpoint the cleanest place to tune a LoRA: change one scale at a time and every difference you see comes from that change.

Wan 2.2 low-noise LoRAs

In our test the low-noise file of a Wan 2.2 image-to-video LoRA changed the clip in the same direction as its Wan 2.1 version, so many newer LoRAs are usable here too.

Request parameters

ParameterRequiredDescription
duration_secondsNoHow long the clip runs. You pay per second. 5 · 10 · Default: 5
flow_shiftNoFlow-matching timestep shift, from 1 to 10. Leave it out for the default (3 at 480p, 5 at 720p). ≥ 1 · ≤ 10
guidance_scaleNoHow strictly the model follows the prompt. ≥ 0 · ≤ 20 · Default: 5
image_urlYesThe picture to start from.
lorasNoLoad your own LoRA files to lock in a style or character. Default: []
negative_promptNoThings you don't want to see.
promptYesDescribe what happens after the opening frame and how the camera moves.
resolutionNoOutput size. Bigger sizes look sharper and cost more. 480p · 720p · Default: 480p
seedNoReuse the same number to get a repeatable result. ≥ 0 · ≤ 2147483647
stepsNoMore steps add detail but take longer. ≥ 1 · ≤ 40 · Default: 30

Pricing

Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.

OptionCredits per run≈ USD
duration_seconds 5 · resolution 480p36$0.36
duration_seconds 10 · resolution 480p54$0.54
duration_seconds 5 · resolution 720p54$0.54
duration_seconds 10 · resolution 720p81$0.81

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

Moving portraits

Turn a still into a shot with a camera move you choose, from a slow push-in to a full orbit, while the face and the outfit stay those of your photo.

Fashion and product stills

An orbit LoRA shows an outfit or an object from every side, starting from one good photograph, which saves a second shoot.

Prompt guide & pro tips

Write the trigger phrase

Effect LoRAs usually need their trigger words, for example the orbit phrase their author lists. Put it in the sentence that describes the camera, as our orbit example does.

Ask for the change

The model stays close to the photo: clothing and setting in the photo tend to stay. Name the action and the change you want early in the prompt, one main action per clip.

Compare at the same seed

Run once with loras empty and once with your LoRA at the same seed; the clips are directly comparable here, so you see exactly what the LoRA does.

Use direct, public links

Use a public link that downloads the .safetensors file itself, such as a Hugging Face "resolve/main" link.

API quick start

Call the Wan 2.1 LoRA API in three steps

  1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
  2. Send the request. POST /jobs/createTask with model alibaba/wan-2.1-lora/image-to-video and an input object that follows the parameter table. The response returns a task ID straight away.
  3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "alibaba/wan-2.1-lora/image-to-video",
  "input": {
    "prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
    "image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
    "resolution": "480p",
    "duration_seconds": 5
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

Wan 2.1 LoRA API questions

How much does the Wan 2.1 LoRA API cost?

Wan 2.1 LoRA starts at 36 credits ($0.36) per run with Image to Video, its cheapest task. Prices by option: 5 · 480p 36 credits per run, 10 · 480p 54 credits per run, 5 · 720p 54 credits per run, 10 · 720p 81 credits per run. Credits are the same as on the website (1 credit = $0.01), new accounts get 30 free credits, and failed tasks are refunded.

What is the model name for Wan 2.1 LoRA in the API?

Put alibaba/wan-2.1-lora/text-to-video for Create Video; alibaba/wan-2.1-lora/image-to-video for Image to Video; alibaba/wan-2.1-lora/video-edit for Edit Video in the model field of POST /jobs/createTask.

Which LoRAs work here?

Files trained for Wan 2.1 14B: text-to-video LoRAs and LoRAs for the 480P or 720P image-to-video checkpoints, which is where most community Wan LoRAs sit. In our tests a Wan 2.2 single-file style LoRA and the low-noise half of a Wan 2.2 pair also took effect. A LoRA for an unrelated model fails the request.

Does the same seed give the same clip?

On image-to-video it did in our test: same seed, same inputs, a byte-identical file, which makes LoRA comparisons clean there. Treat the seed as a way to compare runs fairly rather than a guarantee; the other endpoints can vary.

What do steps, guidance and flow shift do?

steps trades time for detail (30 by default). guidance_scale sets how strictly the clip follows the prompt (5 by default); high guidance with few steps gave us oversaturated frames. flow_shift moves the noise schedule; leave it out unless a LoRA's author recommends a value.

Does it have sound?

No. Clips come back silent; add sound afterwards or with a video-to-audio model.

What are the limits of the Wan 2.1 LoRA API?

Clip length: 5–10 s; Resolutions: 480p · 720p. Requests outside these limits are rejected before anything is charged.

Can I try Wan 2.1 LoRA without writing code?

Yes. The Playground runs Wan 2.1 LoRA on your PopNow credits, needs no API key, and shows the matching code for every run.

All Wan models

Wan 2.2 LoRA runs the newer model with separate motion and detail slots.

More about Wan 2.1 LoRA