Definition — The width-to-height proportion of an image or video, such as 9:16 (vertical), 1:1 (square) or 16:9 (landscape). In social publishing, the placement dictates the ratio.
Each placement has a native ratio: 9:16 for stories, reels and short vertical video; 1:1 and 4:5 for feed posts; 16:9 for landscape video and web headers. Publishing at the placement's native ratio is not cosmetic — mis-sized content gets letterboxed or auto-cropped, and auto-crops routinely cut faces and products.
The important production habit is to generate at the target ratio instead of cropping afterwards. A generation composed for 9:16 places the subject, negative space and background for that frame; cropping a square image to vertical merely amputates a composition that was built for a different shape. Decide the placement first, then generate.
For persona accounts, ratio discipline is part of visual identity: a feed where every post shares the ratio and framing conventions of its Forge Style reads as one coherent body of work — and video placements inherit the same logic, since an image-to-video clip keeps the ratio of its source still.
A reusable style template that fixes scene, lighting, framing and mood for a generation, so a content series stays visually coherent. Presets separate the persona (trained once) from the look (chosen per shoot).
Increasing an image's pixel resolution, typically with an AI model that synthesizes plausible fine detail. Distinct from rendering at a high resolution natively.
Generating a short motion clip (typically 5–10 seconds) from a single still image, preserving the subject and scene while adding camera or subject movement. Used to turn winning stills into motion placements.
See it live with 100 free credits
No card required. Generate with showcase models on the free tier, then train your own persona on any paid plan.