Romann Weber

RMW's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 2 papers 5 months ago

HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling

Paper • 2506.20452 • Published Jun 25 • 19

Guidance in the Frequency Domain Enables High-Fidelity Sampling at Low CFG Scales

Paper • 2506.19713 • Published Jun 24 • 14

authored 2 papers about 1 year ago

Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models

Paper • 2410.02416 • Published Oct 3, 2024 • 33

CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling

Paper • 2310.17347 • Published Oct 26, 2023 • 1

authored 3 papers over 1 year ago

Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion

Paper • 2408.00458 • Published Aug 1, 2024 • 13

No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models

Paper • 2407.02687 • Published Jul 2, 2024 • 25

LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models

Paper • 2405.14477 • Published May 23, 2024 • 20