Introduction
Wan 2.2 LoRA Video extend continues a clip you already have. Send it as video_url with a prompt for what happens next. The final frame of your clip becomes the opening frame of a new Wan 2.2 LoRA image-to-video shot of exactly 5 or 8 seconds, and the two are joined into one MP4: your original first, then the continuation, with the repeated seam frame removed. The new segment also comes back as its own file, so you can keep extending or edit the pieces separately.
Key features
Continuity comes from the last frame. Wardrobe, set, light and where everyone stands carry over because the new segment literally starts on your final frame. Motion does not carry over the same way: the model sees one still, not the whole clip, so describe the movement you want to continue instead of assuming it will keep its speed or direction.
One file back, plus the new piece on its own. The joined MP4 keeps your clip’s frame rate and its framing, with no black bars. To line the seam up, the picture may be trimmed or adjusted by a few percent at the edges. If the model returns a noticeably different shape, the new segment is scaled to fill your frame and centered, cropping what spills over. It is encoded as an H.264 MP4. Wan 2.2 LoRA makes silent video: the sound of your source plays up to the seam and fades out, and the new segment is silent. The second asset in the output is the new segment alone, ready for another extend or for an editor.
Your LoRAs carry over. The three LoRA slots work as on the image-to-video endpoint, each entry a direct weight URL plus a strength from 0 to 4.
Everything else is Wan 2.2 LoRA image-to-video.
Request parameters
| Parameter | Required | Description |
|---|---|---|
duration_seconds | No | How long the clip runs. You pay per second. 5 · 8 · Default: 5 |
high_noise_loras | No | LoRA weights applied to the high-noise expert. Default: [] |
loras | No | Load your own LoRA files to lock in a style or character. Default: [] |
low_noise_loras | No | LoRA weights applied to the low-noise expert. Default: [] |
prompt | Yes | Describe what happens next: the action that follows and the camera move. |
resolution | No | Output size. Bigger sizes look sharper and cost more. 480p · 720p · Default: 480p |
seed | No | Reuse the same number to get a repeatable result. ≥ 0 · ≤ 2147483647 |
video_url | Yes | The clip to work on. |
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.
| Option | Credits per second | ≈ USD |
|---|---|---|
| resolution 480p | 3.6 | $0.036 |
| resolution 720p | 7.2 | $0.072 |
For an exact number before you run, send the same body to POST /jobs/quote.
Use cases
Lengthen a shot that ended too early: a product turntable that stops before the label faces camera, or a walk that cuts before the subject reaches the door. Extend it by a few seconds and describe only the remaining motion.
Build a longer sequence step by step. Because every step starts from a single frame, watch each seam before stacking the next one.
Prompt guide & pro tips
Describe the next beat, not the whole scene. The frame already fixes who and where, so spend the prompt on the action that follows and the camera move. Repeat the camera language your clip ended on, such as a slow push in or a locked shot, so the seam reads as one take.
Trim before you extend. The last frame is the only thing the model sees, so a blurred, mid-cut or heavily compressed ending carries straight into the continuation. Cut your source on a clean, sharp frame first. Sources of up to 60 seconds are accepted as MP4, MOV or WebM.
Keep the resolution consistent. Extending a 720p clip at 480p looks softer next to the original.
Keep the style steady: attach the same LoRAs at the same strengths as on the clip. A LoRA that exists only on the new segment shows up as a visible change at the seam.
API quick start
Call the Wan 2.2 LoRA API in three steps
- Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
- Send the request. POST /jobs/createTask with model alibaba/wan-2.2-lora/video-extend and an input object that follows the parameter table. The response returns a task ID straight away.
- Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(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: $IDEMPOTENCY_KEY" \
-d '{
"model": "alibaba/wan-2.2-lora/video-extend",
"input": {
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
"video_url": "https://media.popnow.ai/effects/flower-bloom-1abd6efb.mp4",
"resolution": "480p",
"duration_seconds": 5
}
}'
# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$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 2.2 LoRA API questions
How much does the Wan 2.2 LoRA API cost?
Wan 2.2 LoRA starts at 18 credits ($0.18) for a 5-second clip with Extend Video, its cheapest task. Prices by option: 480p 3.6 credits per second, 720p 7.2 credits per second. 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 2.2 LoRA in the API?
Put alibaba/wan-2.2-lora/text-to-video for Create Video; alibaba/wan-2.2-lora/image-to-video for Image to Video; alibaba/wan-2.2-lora/video-extend for Extend Video in the model field of POST /jobs/createTask.
How many LoRAs can I attach?
Up to three per slot, and there are three slots: loras, high_noise_loras and low_noise_loras. Each entry is a direct weight URL plus a strength from 0 to 4, defaulting to 1.
What is the difference between the three LoRA slots?
Wan 2.2 denoises in two passes. high_noise_loras attaches to the high-noise expert, where composition and motion are set; low_noise_loras attaches to the low-noise expert, where detail and texture resolve; loras applies to both at once. A LoRA published as a high-noise and a low-noise file goes into the matching two slots.
Where are the weights stored?
On your hosting. Each file is fetched from the URL you supply for the duration of the run and nothing is stored, so weights that must stay private should sit behind a signed link.
Which links work?
A direct download link to the weights file always works. On image-to-video, files may be up to 1 GB and Civitai model pages or Hugging Face /blob/ links are also resolved to the file. On text-to-video, link the .safetensors file itself: a repository page fails the run, and so does anything behind a login.
How long can a clip be?
Exactly five or eight seconds. duration_seconds is an enum, so a value like six is rejected rather than rounded.
What are the limits of the Wan 2.2 LoRA API?
Clip length: 5–8 s; Resolutions: 480p · 720p; Longest input clip: 60 s. Requests outside these limits are rejected before anything is charged.
Can I try Wan 2.2 LoRA without writing code?
Yes. The Playground runs Wan 2.2 LoRA on your PopNow credits, needs no API key, and shows the matching code for every run.
All Wan models
Wan 2.5 adds sound, 1080p and 10-second clips; Wan 2.2 LoRA is the one when you need your own weights.
- Wan 3.0 APIUp to 30-second clips with synced audioFrom 34 credits for a 5-second clip
- Wan 3.0 Prime APIQuicker Wan 3.0 renders, up to 30 seconds with audioFrom 46 credits for a 5-second clip
- Wan 3.0 Pro Prime APIQuicker Wan 3.0 Pro with 2K and 4K outputFrom 176 credits for a 5-second clip
- Wan 3.0 Pro APIWan 3.0 at 1080p, 2K or 4K, up to 30 secondsFrom 108 credits for a 5-second clip
- Wan 2.7 Pro APILarge 4K canvases and nine-image compositesFrom 12 credits per image
- Wan 2.7 APIThinks through the composition, then draws up to four imagesFrom 5 credits per image
- Wan 2.6 Flash APIQuick multi-shot clips from a single imageFrom 17 credits for a 5-second clip
- Wan 2.6 APIMulti-shot sequences with sound at up to 1080pFrom 49 credits for a 5-second clip
- Wan 2.5 API1080p clips with sound that can follow your own audioFrom 34 credits for a 5-second clip
- Wan 2.2 Animate APIDrive a character photo with a reference videoFrom 7.95 credits per second
- Wan 2.2 LoRA APIWan 2.2 video with your LoRAs on either expert passFrom 18 credits for a 5-second clip
- Wan 2.2 APISimple five-second clips at 480p or 720pFrom 36 credits per run
- Wan 2.2 5B LoRA APILight 720p Wan 2.2 clips that load your own LoRAsFrom 18 credits per run
- Wan 2.2 Image LoRA APIWan 2.2 stills with up to nine LoRAs across three slotsFrom 5 credits per image
- Wan 2.1 LoRA APIWan 2.1 video and edits with your own LoRAs, camera moves includedFrom 36 credits per run
- Wan 2.1 Image LoRA APIPhotoreal Wan 2.1 stills and restyles with your LoRAsFrom 5 credits per image
Other video APIs
- MiniMax H3 APIExpressive clips with audio, up to 2KFrom 28 credits for a 5-second clip
- MiniMax H3 Singularity LoRA APICommunity-tuned H3 video that loads your own LoRAsFrom 45 credits for a 5-second clip
- MiniMax H3 LoRA APIMiniMax H3 video with sound and up to three of your LoRAsFrom 38 credits for a 5-second clip
- LTX-2.3 LoRA APILTX-2.3 clips with stereo sound and your own LoRAsFrom 18 credits for a 5-second clip
- LTX-2 19B LoRA APILTX-2 clips with sound and your own LoRA stylesFrom 14 credits for a 5-second clip
