Janus
Janus turns a text prompt into an image. Pick a mode, write the prompt, run it in the studio.
Input
FormPrompt*
Image Size
Num Images
Temperature
Result
Preview
Generated with Janus
Credits·~10s
What Janus is for
Janus is a text-to-image model. You describe the frame and it returns a still image in about 10 seconds, billed at Credits. There is one mode on this page: text to image.
Janus is cheap enough that a generation usually fits the free Knowlify plan's credits. A typical run is about 10 seconds.
Pick Janus for text to image at Credits and ~10s. Compare it with Ai Avatar, Argil Avatar on the related cards below if you need a different look, speed, or input type.
How to use Janus
- 1. Write a still prompt for Janus. Be specific about subject, style, and lens.
- 2. Run it. The prompt opens in the Knowlify studio, where Janus generates.
- 3. Stay in the studio to turn a document or a longer prompt into a narrated video.
What you need
- A prompt that names the subject, style, and framing.
- Image Size (square_hd, square, portrait_4_3, portrait_16_9, and more).
Example prompt
a sumo wrestler standing in falling snow, steam off the skin, IMAX aerial still, golden hour, huge scale, no text, no watermark
Frequently asked questions
How do I run Janus?
Run Janus on Knowlify at /generate/janus. Write the prompt on this page and it opens in the studio, where Janus generates a still image. The same studio also turns documents into full narrated videos.
Where can I use Janus online?
On Knowlify (knowlify.com/generate/janus). You do not need a separate playground. Janus runs in the studio next to document-to-video.
Can I make a longer video with Janus?
Janus itself produces a still image. On Knowlify you can take that output, or skip it and upload a document, and generate a full narrated video with a script you can edit.
What do I need to run Janus?
A text prompt is enough. Janus generates the image from that description in the studio.
How long does Janus take?
Plan on about 10 seconds for a typical run, then whatever queue time the studio has. Video models sit at the high end of that range.
What does DeepSeek Janus-Pro cost?
Knowlify charges this as credits, at the compute cost.
What is DeepSeek Janus-Pro best for?
DeepSeek Janus-Pro is a novel text-to-image model that unifies multimodal understanding and generation through an autoregressive framework. It turns a text prompt into an image.
Do I need an account to use DeepSeek Janus-Pro?
Yes. DeepSeek Janus-Pro runs in the Knowlify studio, which needs a free account. Anything you type on this page comes with you.