GenAI continues to play with different modalities, now anyone can be animated — deepfakes are unstoppable now
What you need just an image of a person and a video to put this person into.
Recent character image animation methods based on diffusion models, such as Animate Anyone, have made significant progress in generating consistent and generalizable character animations. However, these approaches fail to produce reasonable associations between characters and their environments. To address this limitation, we introduce Animate Anyone 2, aiming to animate characters with environment affordance. Beyond extracting motion signals from source video, we additionally capture environmental representations as conditional inputs. The environment is formulated as the region with the exclusion of characters and our model generates characters to populate these regions while maintaining coherence with the environmental context. We propose a shape-agnostic mask strategy that more effectively characterizes the relationship between character and environment. Furthermore, to enhance the fidelity of object interactions, we leverage an object guider to extract features of interacting objects and employ spatial blending for feature injection. We also introduce a pose modulation strategy that enables the model to handle more diverse motion patterns. Experimental results demonstrate the superior performance of the proposed method.
In this paper, we introduce Animate Anyone 2, a novel framework that enables character animation to exhibit environment affordance. We extract environmental information from driving videos, enabling the animated character to preserve its original environment. We pro-pose a novel environment formulation and object injection strategy, facilitating seamless character-environment integration. Moreover, we propose pose modulation that empowers the model to robustly handle diverse motion patterns. Experimental results demonstrate that Animate Anyone 2 achieves high-fidelity generation performance.
