AI Video Models
These are the video generation models you can use on blubiu with one balance of credits. They differ in clip length, resolution, whether they generate sound, what references they accept and how they are priced — the table below lists the current numbers from the platform catalog.
How to choose
- →Need sound with the picture: Seedance 2.0 or Veo 3.1 Fast.
- →Need 2K: MiniMax H3.
- →Keeping a character consistent across clips: Seedance 2.0 (up to 9 reference images), used by reference to video.
- →Cheapest drafts: MiniMax H3 Lite for a few seconds, or Veo 3.1 Fast for a full 8-second clip with sound.
- →Swapping a person or character in existing footage: Wan 3.0, which also takes non-human characters.
- →Making a person in a photo copy the moves from a clip: Kling Motion Control (human figures only); the motion control AI page compares it with the other ways to copy moves.
- →Sharpening a finished clip to 1080P, 2K or 4K: FlashVSR.
All models compared
| Model | Inputs | Length | Resolution | Sound | Price |
|---|---|---|---|---|---|
| Seedance 2.0 | Text, First frame (+ optional last), References (images ≤9, videos ≤3, audio ≤3) | 4–15 s | 480P / 720P / 1080P | Optional | 480P 18.36 · 720P 39.46 · 1080P 98.42 credits/s, 4 s minimum; subscribers 40% off: 480P 11.02 · 720P 23.68 · 1080P 59.06 credits/s; reference video 480P 11.18 · 720P 24.02 · 1080P 59.84 credits/s |
| Seedance 2.0 Fast | Text, First frame (+ optional last), References (images ≤9, videos ≤3, audio ≤3) | 4–15 s | 480P / 720P | Optional | 480P 14.22 · 720P 30.56 credits/s, 4 s minimum; subscribers 40% off: 480P 8.54 · 720P 18.34 credits/s; reference video 480P 8.46 · 720P 18.18 credits/s |
| Seedance 2.0 Mini | Text, First frame (+ optional last), References (images ≤9, videos ≤3, audio ≤3) | 4–15 s | 480P / 720P | Optional | 480P 8.84 · 720P 19 credits/s, 4 s minimum; subscribers 40% off: 480P 5.31 · 720P 11.4 credits/s; reference video 480P 5.38 · 720P 11.58 credits/s |
| VEO 3.1 Fast | Text, First frame (+ optional last) | 8 s | 720P | Optional | 14 credits/clip; subscribers 40% off: 9 credits/clip |
| MiniMax H3 (Hailuo) | Text, References (images ≤9, videos ≤3, audio ≤3) | 5–15 s | 768P / 2K | Silent | 768P 19.4 · 2K 29 credits/s, 5 s minimum; subscribers 40% off: 768P 11.64 · 2K 17.4 credits/s; reference video 768P 16.2 · 2K 27 credits/s |
| MiniMax H3 Lite (Hailuo) | Text, First frame (+ optional last), References (images ≤9, audio ≤3) | 1–15 s | 480P / 768P | Silent | 480P 2 · 768P 4 credits/s, 1 s minimum; subscribers 40% off: 480P 1.2 · 768P 2.4 credits/s |
| Muse Video | Text, First frame (no last frame), References (images ≤4) | 5–15 s | 720P | Optional | 720P 7.4 credits/s, 4 s minimum; subscribers 40% off: 720P 4.44 credits/s |
| Wan 3.0 | Text, First frame (+ optional last), References (images ≤10, videos ≤5, audio ≤5) | 2–15 s | 480P / 720P / 1080P | Optional | 480P 9 · 720P 18 · 1080P 36 credits/s, 2 s minimum; subscribers 40% off: 480P 5.4 · 720P 10.8 · 1080P 21.6 credits/s; reference video seconds are billed at the same rate |
| Wan 3.0 Prime | Text, First frame (+ optional last), References (images ≤10, videos ≤5, audio ≤5) | 2–15 s | 480P / 720P / 1080P | Optional | 480P 13.6 · 720P 28 · 1080P 56 credits/s, 2 s minimum; subscribers 40% off: 480P 8.16 · 720P 16.8 · 1080P 33.6 credits/s; reference video seconds are billed at the same rate |
| Kling Motion Control | One video (up to 30 s), One full-body photo of a person | Same as your video (up to 30 s) | 720P / 1080P | — | 720P 12 · 1080P 20 credits per second of your video; subscribers 40% off: 720P 7.2 · 1080P 12 credits/s |
| FlashVSR | One video (up to 120 s) | Same as your video (up to 120 s) | 720P / 1080P / 2K / 4K | — | 720P 4 · 1080P 6 · 2K 7 · 4K 12 credits per second of your video; subscribers 40% off: 720P 2.4 · 1080P 3.6 · 2K 4.2 · 4K 7.2 credits/s |
| AI Lip-Sync | One portrait + one audio clip (up to 60 s) | Same as your audio (up to 60 s) | — | — | 720P 4 credits/s, 1 s minimum; subscribers 40% off: 720P 2.4 credits/s |
Standard prices, read live from the platform catalog; once signed in, the Generate button shows your account's actual price.
Make 4–15 second videos with sound from text, a first frame or up to 9 reference images with ByteDance's Seedance 2.0 — Mini, Fast and 2.0 compared.
Use MiniMax H3, the Hailuo video model, for 2K clips with reference images and videos, or H3 Lite for the cheapest silent drafts from 1 second.
Generate an 8-second 720p clip with optional sound using Google's Veo 3.1 Fast, from text or from a first and last frame. One fixed price per clip.
Use Alibaba's Wan 3.0 for 2–15 second videos with sound from text, a first frame or reference images, or to replace the person in a video.
Run Kling Motion Control 2.6 online: a full-body photo copies the moves from a 3–30 second video, at 720P or 1080P. No Kling account needed; try it free.
Upscale an MP4 or MOV up to 120 seconds to 720P, 1080P, 2K or 4K with FlashVSR, a video super-resolution model. Billed per source second.
See image models →Tools built on these video models
Create Video with AI →
Create video with AI from a sentence, a first frame, first and last frames or up to 9 reference images: 1–15 second clips with Seedance, Veo, MiniMax and Wan.
AI Text to Video Generator →
Turn a written description into a 1–15 second video with Seedance, MiniMax H3, Veo and more — no images needed.
AI Image to Video Generator →
Upload an image as the first frame, describe the motion and generate a video with Seedance, Veo 3.1, MiniMax H3 Lite or Wan 3.0.
Talking Photo AI →
Talking photo AI that turns one portrait into a talking head video: type a script or upload audio, and the face lip-syncs it. Works on characters too.
AI Video Upscaler →
Free online AI video upscaler: upscale an MP4 or MOV up to 120 seconds to 1080P, 2K or 4K. Same length and frame rate, billed per source second.
AI Motion Transfer →
Upload a full-body photo of a person and a motion video up to 30 seconds; the person performs the same dance or moves at 720P or 1080P.
Motion Control AI →
Motion control AI copies the moves from a reference video onto a photo of a person: upload both, get a 3–30 second video at 720P or 1080P. Try it free.
AI Character Swap for Video →
AI character swap for video: upload a clip and one or two images of your character to replace the person in it. Motion, camera and lighting stay.
Recast Video with AI →
Recast any video with your own character: upload a clip and one or two character images, and the motion, camera, background and lighting stay as shot.
AI video models FAQ
Which AI video model should I start with?
Start from what the clip needs. For sound, Seedance 2.0 or Veo 3.1 Fast; for 2K, MiniMax H3; for the same character across clips, Seedance 2.0 with reference images. Draft on the cheapest option at a low resolution, then rerun the keeper.
Do I need a separate subscription for each model?
No. Every model here runs on one balance of blubiu credits. The table lists standard prices; the Generate button shows the exact cost for your account before you confirm. See pricing for plans and credit packs.
Can I start a video from my own image?
Yes. Models that accept a first frame work with image to video; models with first and last frames work with first and last frame video; the Inputs column shows which model takes what.
Which models generate sound?
The Sound column says it per model; at the time of checking, Seedance 2.0 and Veo 3.1 Fast generate audio together with the picture. Check the column for the others before you rely on sound.
Are failed generations charged?
No. Failed, refused or cancelled generations are refunded automatically, on every model.
How do I get a sharper or longer result?
For sharpness, run the finished clip through the AI video upscaler. For length, generate shot by shot and join them; first and last frame video lets one shot end exactly where the next begins.