All docs

Choosing models and quality

Every runime film is rendered by a stack of AI models: one draws your images, one animates them into video, and separate ones handle voice, music, and sound effects. You can hand-pick each of these, or leave them on Auto and let runime choose the best model for each task and quality level. Auto is the default, and for most projects it's the right call — but the choice is always yours, whole-film or shot-by-shot.

Auto: let runime pick per task

Auto (shown as "Oto") is the first option in every model list and the default for new projects. Instead of using one model for everything, it picks the best-fitting model for each specific job — character design, a storyboard still, a moving shot, a line of dialogue, the score — because no single model is best at all of them.

Auto is also context-aware. For example, if your film features children, it steers video toward a child-safe model rather than one that blocks minors' faces; for a headscarf character or a photoreal look, it favors the model that handles that best. If you'd rather not think about any of this, Auto is the recommended setting.

Where to set models: whole-film vs. per-shot

There are two levels of control. In your project settings you set film-wide defaults for the image model, video model, voice, music, sound effects, and even the screenwriter — these apply to everything runime generates. Each list starts with Oto, so leaving them untouched keeps the whole film on Auto.

Inside the shot editor you can override the image and video model for a single shot. This is the tool for a specific problem — say one hero shot where you want a more consistent look — without changing the rest of the film. A per-shot choice always wins over the project default for that shot.

The line-up you can choose from

For images you can pick from options like Nano Banana, Flux, Midjourney, GPT Image, Imagen 4, Ideogram, Stable Diffusion 3.5, and Grok Imagine. For video: Veo 3, Sora, Runway Gen-4.5, Kling, Luma, Pika, Hailuo, and Grok Imagine. Voice runs on ElevenLabs, Play.ht, or Fish Audio; music on Suno, Udio, ElevenLabs Music, or AIVA; sound effects on ElevenLabs SFX, MMAudio, or Stable Audio. The screenwriter can run on Gemini 2.5 Pro or DeepSeek V3.1.

One safety net matters: if you pick a model that physically can't do a job (for example, a shot that needs start-and-end keyframes on a model that doesn't support them), runime won't force it — it automatically switches to a capable model so the shot still renders correctly.

Choosing by consistency

When you open the image or video model picker in the shot editor, each model shows a small consistency rating (like ~88%). Consistency is how reliably a model keeps your subjects, motion, and physics coherent — no faces morphing, no objects floating or clipping through solid things, no drift across a set. It's relative guidance, not a promise.

Use it as a tie-breaker: if two models suit your style, the higher consistency score is the safer pick for a shot with a lot of movement, a camera turn, or a character reveal. If you're not sure, Auto already weighs this for you.

Quality is separate from the model

Which model renders a shot and how sharp the final file is are two different settings. To stay fast and affordable, runime generates your film at 720p while you work. You only raise the quality when you download the finished film.

In the export dialog you choose a resolution tier — 720p (standard), 1080p, or 4K — where 1080p and 4K use real AI super-resolution, adding genuine detail rather than just resizing. You can also toggle a cinematic tone (film grain and color grade) and smooth 60fps motion. These add-ons cost tokens and are priced up front; once you've produced a given tier, re-downloading that exact version is free.