Skip to main content
Framesail AI
Docs

Pipeline steps

Segment renders: images, clips, and models

Segment rendering turns each storyboard panel into an image or a video clip. Model choice is per job, per run — there is no global image or video provider setting — and every shot can be regenerated on its own without touching the rest. You can also upload your own image for any segment.

Image models

Video models

Current options: Wan 2.7, Kling v3 Standard, Kling v3 Pro, Kling 2.6 Pro, Seedance 2 Pro, Seedance 2 Fast, Hailuo 2.3 Pro, Hailuo 2.3 Fast, and Veo 3.1. Each model exposes its own settings:

Clip duration is not a setting: it is derived automatically from the segment's narration length and snapped to the model's allowed durations (Veo 3.1 clips are fixed at 8 seconds, for example).

Prompts and the expert drawer

Every generation step's prompt is built from named sections. In the expert drawer you can override the editable sections per run — overrides are validated server-side — and reset any section back to its default. The drawer is also where the model picker and per-model settings live. Overrides persist at the scope you set them: project, style, asset, segment asset, or voice block.

Regeneration rules

Each render draws on the segment's tagged reference images, which is how a shot fifty scenes in still matches shot one — see how character consistency works.