Enhanced Controllability of Diffusion Models via Feature Disentanglement and Realism-Enhanced Sampling Methods

no code implementations • 28 Feb 2023 • Wonwoong Cho, Hareesh Ravi, Midhun Harikumar, Vinh Khuc, Krishna Kumar Singh, Jingwan Lu, David I. Inouye, Ajinkya Kale

Second, we propose timestep-dependent weight scheduling for content and style features to further improve the performance.

Denoising Disentanglement +4

Controlled and Conditional Text to Image Generation with Diffusion Prior

no code implementations • 23 Feb 2023 • Pranav Aggarwal, Hareesh Ravi, Naveen Marri, Sachin Kelkar, Fengbin Chen, Vinh Khuc, Midhun Harikumar, Ritiz Tambi, Sudharshan Reddy Kakumanu, Purvak Lapsiya, Alvin Ghouas, Sarah Saber, Malavika Ramprasad, Baldo Faieta, Ajinkya Kale

We observe that Diffusion Prior can be used in a memory and compute efficient way to constrain the generation to a specific domain without altering the larger Diffusion Decoder.

Decoder Denoising +2