Fresh out of the oven
These tools are new, so the odd thing may still wobble. If something looks wrong, it probably is. Tell us and we will sort it.
Fresh out of the oven
These tools are new, so the odd thing may still wobble. If something looks wrong, it probably is. Tell us and we will sort it.
Fresh out of the oven
These tools are new, so the odd thing may still wobble. If something looks wrong, it probably is. Tell us and we will sort it.
Pinnora's AI carousel maker builds a deck of 3 to 10 slides from one angle you write. You set Slides on the ruler, pick 1:1, 4:5, or 9:16 under Aspect ratio, and choose a Visual register: Swiss grid, Editorial, Bold pop, Minimalist, Muted luxury, or Data explainer. Visual continuity decides how tightly the slides hold together. Tight renders slide one first, then references it plus a style anchor image on every slide after, so the deck reads as one hand. The copy pass writes a headline, body, and art direction per slide against your brand grounding, then the headline is typeset into the pixels. Final slide CTA holds the closing ask in 60 characters or less. The default image model is openai/gpt-image-2.
The tool is open above. This is the short version of what to do with it.
The brief field is called Carousel angle. Name the argument and who should be nodding by the last slide, such as "5 mistakes founders make pricing their first product". Slide one becomes the hook, the last slide becomes the ask, and the middle band carries the story you named.
Under Angle and format, drag Slides anywhere from 3 to 10. It opens at 7. Then pick Aspect ratio: Square 1:1, Portrait 4:5, or Vertical 9:16. That ratio is what the pixels are rendered at, not a suggestion the copy model can talk you out of.
Look and flow holds two dials. Visual register picks the hand: Swiss grid, Editorial, Bold pop, Minimalist, Muted luxury, or Data explainer. Visual continuity picks Tight, Varied, or Free, which decides whether every slide references the style anchor and slide one, or is free to drift.
Type the closing ask in Final slide CTA, up to 60 characters, and leave Model on Auto for openai/gpt-image-2 or name another image model. The run writes every slide's copy first, renders the style anchor, then renders slide one and fans the rest out four at a time, each headline typeset into the frame.
Short answers to what people ask before they start.
The rest of the family. Every one is free to try and runs on the same engine.
