CoreLesson 330 min

Frame Control: First, Last, and Transitions

By the end of this lesson you can
  • Build all three image-to-video request shapes - first frame, last frame, and first & last - with correctly labeled roles
  • Predict ratio behavior in i2va mode, including what happens to an explicitly passed ratio value
  • Decide when frame control is the right tool and when reference generation would serve the shot better

Text-to-video gives the model total freedom; frame control takes some of it away on purpose. Pin a first_frame and you have dictated exactly where the clip begins. Pin a last_frame and you have dictated where it must arrive. Pin both and the generation's job is reduced to the most cinematic problem there is: get from this image to that one, plausibly, in the time allowed.

The three request shapes come straight from the documented combinations, and you already know the grammar from lesson 1:

Core — locked

Unlock “Frame Control: First, Last, and Transitions”

The 4-lesson Foundation module is free and always will be — you have already read the part most guides get wrong. The paid lessons go deeper, with labs, knowledge checks, and every technical claim verified against live documentation.

MiniMax H3 — Complete Course
The whole course, one purchase
$129one-time

Already bought it? Sign in with the email you used at checkout.