AI Video Generator from Text and Images
Create videos from a prompt or a source frame. See the exact price before you start
About the service
AI video generator from text and images
To make a video with AI, describe a scene in text or upload a photo to animate — the model generates a 4 to 30 second clip at up to 1080p, with sound on most models. The price is shown before launch: 5 seconds at 480p start at $0.16, and WildClips v4.4 can be paid with the daily bonus. No subscription, and Problembo adds no watermark.
Examples
How to create a video with AI
- Choose a model and mode: text, first frame, last frame, first and last frames, or reference media.
- Describe the scene, camera movement, action, lighting, and style.
- Sign in and set the duration, aspect ratio, resolution, and audio when the model supports them.
- Check the exact price and start the task. Download the finished video from the result page.
This creates a new clip rather than editing an existing video, so review the result before publishing.
How to turn a photo into a video
- Pick a model with the "First frame" mode: Grok Imagine Video 1.5, WildClips v4.4, or MomentFlow.
- Upload the photo — the clip starts from it. Match the aspect ratio to the photo.
- Describe motion rather than what is already in the picture: what people and objects do and how the camera behaves ("the camera slowly moves in", "the camera is still").
- For a more controlled transition, add a last frame too — WildClips and MomentFlow support it.
Clean up an old or damaged photo first in the AI photo editor or enhance its quality: the video model carries over defects from the first frame.
Models and prices
| Model | Modes | Duration | Resolution | Price per 5 s (480p / 720p) | Payment |
|---|---|---|---|---|---|
| Grok Imagine Video 1.5 | Text, first frame, up to 7 references; sound | 4–15 s | 480p, 720p | $0.16 / $0.28 | Paid balance |
| MomentFlow v5.2 | Text, frames, up to 30 images and 10 videos | 4–30 s | up to 1080p | $0.98 / $2.21 | Paid balance |
| MomentFlow v5 Fast | Text, frames, and reference media | 5, 10, 15 s | 480p, 720p | $0.41 / $0.87 | Paid balance |
| WildClips v4.4 | Frames or up to 4 references; sound; Fast/Quality | 5–15 s | 480p, 720p | $0.22 / $0.50 | Bonus or paid |
| WildClips v4.3 | First, last, or both frames; sound | 5, 10, 15 s | 480p, 720p | $0.22 / $0.50 | Paid balance |
| Framy NSFW v1.7 | First frame; sound; 18+ model | 4–20 s | 480p, 720p | $0.26 / $0.38 | Bonus or paid |
| Framy NSFW v1.5 | First frame; sound; 18+ model | 5–30 s | — | $0.30 | Bonus or paid |
The price grows in proportion to duration. WildClips v4.4 prices are for Fast mode; Quality costs about twice as much. MomentFlow v5.2 at 1080p costs $5.53 for 5 seconds. Adult-rated models require age confirmation, and all generations must comply with the service rules and applicable law. Models and prices may change — the form always shows current models, settings, and prices.
Which model should you choose?
| Task | Model |
|---|---|
| Test an idea cheaply, video from text | Grok Imagine Video 1.5 at 480p |
| Animate a photo for free with the bonus | WildClips v4.4 at 480p |
| Transition between two set frames | WildClips v4.4 or v4.3 |
| A clip up to 30 seconds long or 1080p | MomentFlow v5.2 |
| A scene built from several references | MomentFlow v5.2 or v5 Fast |
| Reels and Shorts | Any model with the 9:16 format |
Price and daily bonus
Pay for results, not a subscription: you pay only for the selected generation, and the exact price is shown before launch. Your bonus balance can be restored up to $0.60 once per UTC day. Recent paying users receive it automatically; others claim it on Daily bonus.
WildClips v4.4, Framy NSFW v1.7, and v1.5 currently accept bonus funds for video generation. Other models require paid funds. The bonus must cover the full task price: for example, it covers two 5-second WildClips v4.4 clips at 480p or one at 720p. See pricing for details.
Frequently asked questions
Can I turn a photo into a video for free?
Yes, after signing in and within the daily bonus: choose WildClips v4.4 — 5 seconds at 480p cost about $0.22. Other models require paid funds.
Do I need an account?
The model catalog and price quote are available without signing in. Uploading files and starting a generation require an account.
Do the videos have sound?
Grok Imagine Video 1.5, WildClips, and Framy always generate sound; MomentFlow lets you turn it on or off.
Which files can I upload?
Frames and reference images support JPG, JPEG, PNG, and WebP up to about 15 MB. Compatible models also accept reference videos in MP4, MOV, and WebM up to 100 MB.
Will the video have a watermark?
Problembo does not add its own visible watermark to downloaded videos.
Can I use the result commercially?
Commercial use is allowed for generations paid while you have a positive paid balance, subject to third-party rights and the selected model's terms. Do not use bonus-funded generations commercially.
How long are results stored?
3 days, or 30 days if your paid balance is at least $1. Files are then deleted automatically and permanently. See the privacy policy.
What's new
- Reduced video generation prices for MomentFlow v5.2 across all available resolutions, both with and without a video reference.
- Also added support for 1080p resolution.
- Added xAI's new video model, Grok Imagine Video 1.5. It creates videos from text or images up to 15 seconds long at 480p or 720p.
- The model generates audio alongside the video, including speech, music, sound effects, and ambience, while synchronizing lip movements with dialogue.
- Users particularly praise its speed, faithful preservation of the source image, and short-scene quality. Complex motion and voice generation can be inconsistent, so the model works best for concise clips with a clear prompt.
- Added MomentFlow v5.2. The new version generates videos up to 30 seconds instead of 15, handles longer narratives and scene transitions better, and maintains stronger visual consistency. Up to 30 images and 10 videos can be used as references.
- Reduced MomentFlow v5 Fast generation prices across all available resolutions, both with and without a video reference.
- WildClips v4.0 is now available with native stereo audio: the model handles dialogue voiceovers especially well, synchronizes speech with on-screen action, and adds environmental sounds.
- Eleven languages are supported reliably: Russian, English, Chinese, Arabic, French, German, Italian, Japanese, Korean, Portuguese, and Spanish.
- Videos can be generated at up to 2K resolution and up to 15 seconds long.
- Text, first and last frames, images, video, and audio can be used as references (soon).
- MomentFlow v5 and MomentFlow v5 Fast now support attaching a video file as a reference.
- A reference video helps preserve motion and style from the source clip, for example when you want to continue a video.
Framy has been updated to version 1.5, and this is no cosmetic patch — it's a major engine upgrade.
What's New
Image Quality
The latent space has been rebuilt with an updated VAE trained on higher-quality data. In practice this means: hair finally looks like hair, text is legible, and fine facial details no longer dissolve into mush. Visual artifacts have been noticeably reduced.
Audio Out of the Box
Framy 1.5 generates synchronized audio in a single pass — dialogue, ambience, sound effects. An updated vocoder has improved speech intelligibility, and cross-modal alignment has reduced lip-sync and timing drift.
Motion and Consistency
The image-to-video mode has been significantly improved: fewer "frozen" frames, fewer spontaneous panning shots, and better preservation of the source image's visual integrity.
Native Vertical Video
For the first time, vertical generation up to 1080×1920 is supported — the model is trained on portrait data rather than cropping from landscape. Reels and Shorts can now be fed directly.
The text encoder has been scaled up 4×, making the model significantly better at understanding complex prompts describing camera angles, character movements, and scene composition.
Prompt Enhancer
Another major bonus is a powerful prompt enhancer. It helps turn a rough request into a more precise and expressive scene description, carefully refining motion, camera angles, dialogue, and atmosphere so the final video lands closer to the original idea on the first try.
In short, Framy 1.5 is one of those cases where the version number is being modest.