by AlibabaVideo
Wan 2.1 LoRA
Wan 2.1 video and edits with your own LoRAs, camera moves included
- Up to 720p
- 5–10s clips
- Loads your own LoRA
From 36 credits per run≈ $0.36· Create Video
What it's like to use
Wan 2.1 LoRA runs Alibaba's open 14B Wan 2.1 video model with up to three of your own LoRAs, for text to video, image to video and video to video. Clips run 5 or 10 seconds at up to 720p, and camera LoRAs can add an orbit or dolly to a still.
Good for
- One character or style held across many clips
- Camera orbits and dollies added to a photo
- Restyling your own footage while keeping its motion and timing
Real results from Wan 2.1 LoRA
Every image and clip here was generated with Wan 2.1 LoRA. Hit Recreate to open it in the studio with the same prompt and settings.
InputBring your own image
InputBring your own image
Bring your own clip
What Wan 2.1 LoRA can do
Each mode opens in the studio with Wan 2.1 LoRA already picked. The price shows before you generate.
How to prompt Wan 2.1 LoRA
- Use LoRAs trained for Wan 2.1 14B, including the image-to-video checkpoints; many Wan 2.2 style LoRAs work too.
- Link the .safetensors file itself, such as a Hugging Face resolve/main link.
- Judge a LoRA on image to video with the seed held: the same inputs give the same clip, so the difference is the LoRA.
Settings worth knowing
Everything else has a sensible default, so you can type a prompt and go.
resolution480p · 720p- Output size. Bigger sizes look sharper and cost more.
aspect_ratio16:9 · 9:16- The shape of the frame: wide, square or tall.
duration_seconds5s · 10s- How long the clip runs. You pay per second.
image_url- The picture to start from.
video_url- The clip to work on.
negative_prompt- Things you don't want to see.
seed0–2147483647- Reuse the same number to get a repeatable result.
loras≤ 3- Load your own LoRA files to lock in a style or character.
strength0.1–1- How far the result may move away from your input.
How it compares
Same kind of job, different strengths and prices.
Wan 2.2 LoRA runs the newer model with separate motion and detail slots.
Good to know
Clips are silent, 5 or 10 seconds, in 16:9 or 9:16.
Questions about Wan 2.1 LoRA
How much does Wan 2.1 LoRA cost?
On PopNow, the cheapest run of Wan 2.1 LoRA costs 36 credits ($0.36) per run. Larger sizes cost more: 480p 36 · 720p 54. You pay with credits (1 credit = $0.01), the exact cost shows on the Generate button before you start, and failed generations are refunded automatically.
What can Wan 2.1 LoRA do?
On PopNow, Wan 2.1 LoRA works in these modes: Create Video, Image to Video, and Edit Video. Pick one in the studio and add a prompt or an upload.
How long and how sharp are Wan 2.1 LoRA videos?
Clips run 5–10s at up to 720p.
How should I write prompts for Wan 2.1 LoRA?
Use LoRAs trained for Wan 2.1 14B, including the image-to-video checkpoints; many Wan 2.2 style LoRAs work too. Link the .safetensors file itself, such as a Hugging Face resolve/main link. Judge a LoRA on image to video with the seed held: the same inputs give the same clip, so the difference is the LoRA.
Wan 2.1 LoRA or Wan 2.2 LoRA?
Wan 2.2 LoRA runs the newer model with separate motion and detail slots.
Do I need to install anything to use Wan 2.1 LoRA?
No. Wan 2.1 LoRA runs in your browser on PopNow: write a prompt or add a file, choose the settings and download the result. Sign up and you can generate straight away.
Make something with Wan 2.1 LoRA
Type an idea, pick your settings and see the price before you hit Generate.

