Video generation
Generate uncensored AI video from a prompt or from a still
Vellria generates uncensored AI video: you write a prompt that is not rewritten or softened before it renders, pick a video model from the catalog, and get a finished clip back. A clip can begin from a written description alone or from a still that becomes its opening frame, and those are two different models in the catalog rather than two settings on one.
A clip renders as a single take
A video model does not build a timeline. It renders the whole clip in one pass, and there is no point mid-render where you can step in, cut a beat, or change your mind about the camera. What you asked for arrives complete or it does not arrive. That makes the prompt the edit: the action you describe is the action you get, first frame to last.
So write the whole shot before you run it, not the first half of it. Say where the subject starts, what changes, and where it ends up. Then iterate by re-running: change a verb, a light, or a camera word, and compare the takes. Steering happens between runs, which is why it pays to settle the framing and the movement on a short draft before you commit to a long clip at the top of a model's range. Billing and the mechanics of starting a run are the same for video as for stills, and the uncensored image generation page sets them out.
Models
Seedance 2.5 Video
A cinematic video model. Long scenes and natural camera movement.
Text to video
from 28 credits / s
Seedance 2.5 Image Video
Takes the image you provide as the first frame and animates it into a long scene.
Image to video
from 28 credits / s
Seedance 2.0 Fast Video
The cheaper Seedance line, with seven aspect ratios to choose from.
Text to video
from 5 credits / s
Seedance 2.0 Fast Image Video
Takes your image as the first frame, and still lets you choose the frame shape.
Image to video
from 5 credits / s
MiniMax H3 Video
Fast, economical video generation. Straight from text to scene.
Text to video
from 5 credits / s
MiniMax H3 Image Video
Takes the image you provide as the first frame and animates it.
Image to video
from 5 credits / s
MiniMax H3 Max Video
The higher-priced MiniMax tier. Six aspect ratios, on a ladder that reaches 4K.
Text to video
from 8 credits / s
MiniMax H3 Max Image Video
Takes your image as the first frame and animates it at the higher-priced MiniMax tier.
Image to video
from 8 credits / s
HappyHorse 1.1 Video
A video model that reaches 1080p. Nine aspect ratios, 3–15 seconds.
Text to video
from 11 credits / s
HappyHorse 1.1 Image Video
Takes your image as the first frame and animates it up to 1080p.
Image to video
from 11 credits / s
Wan 3.0 Video
A single scene up to 30 seconds. Six frame shapes, picked from a fixed list.
Text to video
from 8 credits / s
Wan 3.0 Image Video
Takes your image as the first frame and animates it for up to 30 seconds.
Image to video
from 8 credits / s
Wan 3.0 Pro Video
The large version of Wan 3.0 Video. Higher detail and steadier motion.
Text to video
from 11 credits / s
Wan 3.0 Pro Image Video
Starts from the first frame and continues with Pro's detail and motion quality.
Image to video
from 11 credits / sMotion has to be written down, not implied
A still prompt describes a frame. A video prompt has to describe a frame and then what happens to it. The subject moves and the camera moves, and a model handed nothing but scenery will decide both on your behalf. Walks toward the door and turns away from the door are different clips with identical set dressing, and the whole difference lives in the verb you wrote.
Camera language is the part most people leave out. A slow dolly, a locked-off frame, a handheld drift and a push-in read as different shots, and omitting the camera does not give you a static one, it gives you an arbitrary one. Pacing works the same way. Say whether the action is a single beat or a sequence of them, because the model has to fit whatever you described into the length you asked for, and an action written for twice that length arrives rushed.
The two routes answer different questions
Working from a description alone is for a shot that does not exist yet: you are asking for a composition as well as for movement, and everything in the frame has to be in the text. Working from a still is for a shot you have already framed. The composition is settled before the run begins, so the whole render goes into motion rather than into deciding what the scene looks like.
There is no third route on the video side. No model here reads pictures as evidence of who should appear and composes the shot around them, so a subject that has to look a particular way is settled while the work is still an image, on an editing model, and the frame you keep is what goes to video. What you hand over, in other words, is a statement about which decisions you have already made.
The frame shape is decided before the run, not after
Some video models take an aspect ratio as part of the request, and on some of those it is required rather than optional. Send a ratio to a model that does not offer one and the request is refused rather than silently accepted, which is the behaviour you want: a clip that came back in a shape you did not choose, with no error to explain it, is worse than a rejected request.
Where a still becomes the opening frame, that picture fixes the shape too, and there is no aspect ratio left to pick afterwards. So crop before you upload. Cropping the finished clip instead means throwing away pixels the model spent your credits rendering, and re-framing a composition that was built for the wider box.
Continuity across shots is the hard part
A clip on its own is the easy case. A run of clips that look like the same production is not, because nothing carries between runs by itself. Each take is generated from scratch, so a character can return with a different face, a room with different furniture, a key light from a different side, even when the wording barely moved. That is the work, not a defect in any particular model.
The catalog gives you one handle on it, and it is the opening frame. Make the frame on an image model, where a character can be supplied as a reference picture rather than described again, keep that file, and animate it. The still then carries the face, the wardrobe and the light into the clip as fact rather than as a sentence waiting to be reinterpreted. And keep your wording stable between takes, since a rewritten description is a new negotiation over everything you did not intend to change.
Frequently asked questions
What does uncensored mean on the video side?
That your wording is not rewritten or softened before it renders, and that fictional adult content is allowed. Two things are refused outright and can suspend or close the account: anyone under age, and real people used without their consent. The rules page sets out the policy in full, including the age requirement the terms attach to every account.
Can I trim or extend a clip after it renders?
Not inside the generator. A take runs start to finish once it begins, and there is no mid-render checkpoint to cut at or continue from. You change the result by changing the prompt and running again, or by taking the downloaded file into your own editor. Plan the clip as one complete take before you commit to it.
Can I animate a picture I already have?
Yes, on the models that take a still and use it as the opening frame. Crop it first, because that picture also fixes the shape of the clip. No video model here reads a picture as evidence and composes the shot around it, so a file that is not the frame you want the clip to open on belongs on an editing model first.
Why does my character look different in every clip?
Because nothing carries between runs. Each take is built from scratch, so a description alone is re-negotiated every time and lands somewhere slightly different. Supply the character instead of describing it: settle it on an image model, then feed that same opening frame into every take in the sequence, and keep the wording steady around it.
How do I decide how long a clip should be?
Write the action first, then match the length to it. The model has to fit whatever you described into the duration you asked for, so a single beat stretched too long drifts and a sequence squeezed too short arrives hurried. Each model page lists the durations that model accepts, and the range is not the same across the catalog.