FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation (youtu.be)
Abstract...
SD.Next update for 03-19-2024 (github.com)
Introducing Stable Video 3D: Quality Novel View Synthesis and 3D Generation from Single Images — Stability AI (stability.ai)
Stability AI and Anime Chain Consider Conducting Joint Research into Generative AI for the Anime Industry (medium.com)
What are the chances this research will be open source?
LightIt: Illumination Modeling and Control for Diffusion Models (CVPR'24) (youtu.be)
Abstract...
Stability AI, OTOY, Endeavor, and The Render Network Join Forces to Develop Next Generation AI Models, IP Rights Systems, and Open Standards Powered by Decentralized GPU Computing (home.otoy.com)
Visual Style Prompting with Swapping Self-Attention (github.com)
Abstract...
Eta Inversion: Designing an Optimal Eta Function for Diffusion-based Real Image Editing (i.imgur.com)
Abstract...
Introducing: Fluxa Avataria (github.com)
cross-posted from: lemmy.dbzer0.com/post/16564872...
Midjourney bans all Stability AI employees over alleged data scraping (www.theverge.com)
How to fix hands in Stable Diffusion - Stable Diffusion Art (stable-diffusion-art.com)
Z-L-D/TripoSR webui: A TriposR implementation for WebUI (github.com)
NVIDIA TensorRT Accelerates Stable Diffusion Nearly 2x Faster with 8-bit Post-Training Quantization | NVIDIA Technical Blog (developer.nvidia.com)
PIXART-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation (imgur.com)
Abstract...
siliconflow/OneDiff v0.12.1 released An out-of-the-box acceleration library for diffusion models. (github.com)
ResAdapter : Domain Consistent Resolution Adapter for Diffusion Models (res-adapter.github.io)
Abstract...
Stable Diffusion 3: Research Paper — Stability AI (stability.ai)
PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis (i.imgur.com)
Abstract...
Sane explanation of FreeU attributes
So I recently switched to ForgeUI and they have plenty of features integrated out of the box....
Haoming02/SD Webui Vectorscope CC An Extension for A1111 WebUI that performs Offset Noise* natively (github.com)
This is an Extension for the Automatic1111 Webui, which performs a kind of Offset Noise natively, allowing you to adjust the brightness, contrast, and color of the generations.
Introducing TripoSR: Fast 3D Object Generation from Single Images — Stability AI (stability.ai)
ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models (youtu.be)
Abstract...