Am I mistaken in thinking this was already doable with diffusion models?
Not with any amount of temporal cohesion. This is using neural rendering that can stay consistent across arbitrary lights and their movement. But the authors chose to go proprietary, hopefully we’ll get some open alternatives in the near future.
alt Hacker News
Not with any amount of temporal cohesion. This is using neural rendering that can stay consistent across arbitrary lights and their movement. But the authors chose to go proprietary, hopefully we’ll get some open alternatives in the near future.