Translations:Diffusion Models Are Real-Time Game Engines/28/en

We re-purpose a pre-trained text-to-image diffusion model, Stable Diffusion v1.4 (Rombach et al., 2022). We condition the model $f_{\theta }$ on trajectories $T\sim {\mathcal {T}}_{agent}$, i.e., on a sequence of previous actions $a_{<n}$ and observations (frames) $o_{<n}$ and remove all text conditioning. Specifically, to condition on actions, we simply learn an embedding $A_{emb}$ from each action (e.g., a specific key press) into a single token and replace the cross attention from the text into this encoded actions sequence. In order to condition on observations (i.e., previous frames), we encode them into latent space using the auto-encoder $\phi$ and concatenate them in the latent channels dimension to the noised latents (see Figure 3). We also experimented conditioning on these past observations via cross-attention but observed no meaningful improvements.