In-Video Instructions: Visual Signals as Generative Control
This addresses the problem of precise, multi-object control in video generation for users needing fine-grained visual guidance, representing a novel paradigm rather than an incremental improvement.
The paper tackles controllable image-to-video generation by using visual signals like arrows or text embedded in frames as instructions, enabling spatial-aware control over multiple objects. Experiments on models like Veo 3.1 show reliable interpretation of these instructions in complex scenarios.
Large-scale video generative models have recently demonstrated strong visual capabilities, enabling the prediction of future frames that adhere to the logical and physical cues in the current observation. In this work, we investigate whether such capabilities can be harnessed for controllable image-to-video generation by interpreting visual signals embedded within the frames as instructions, a paradigm we term In-Video Instruction. In contrast to prompt-based control, which provides textual descriptions that are inherently global and coarse, In-Video Instruction encodes user guidance directly into the visual domain through elements such as overlaid text, arrows, or trajectories. This enables explicit, spatial-aware, and unambiguous correspondences between visual subjects and their intended actions by assigning distinct instructions to different objects. Extensive experiments on three state-of-the-art generators, including Veo 3.1, Kling 2.5, and Wan 2.2, show that video models can reliably interpret and execute such visually embedded instructions, particularly in complex multi-object scenarios.