Stable Diffusion v1.4
PulseAugur coverage of Stable Diffusion v1.4 — every cluster mentioning Stable Diffusion v1.4 across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
ShieldCLIP framework enhances safety alignment for multimodal models
Researchers have introduced ShieldCLIP, a novel framework designed to enhance safety alignment in multimodal foundation models by selectively addressing harmful content. Unlike previous methods that treat all generated …
-
New TEA framework enhances concept erasure in text-to-image models
Researchers have developed a new framework called TEA (Text Encoder Alignment) to improve concept erasure in text-to-image diffusion models. This method fine-tunes only the text encoder, keeping the generative backbone …
-
MapRoute++ advances AI concept unlearning with semantic routing
Researchers have developed MapRoute++, a novel method for visual concept unlearning in AI models. This approach builds upon the previous MapRoute technique by incorporating task-specific training objectives and richer c…
-
AI generates novel motifs for Indonesian Ulos textiles
Researchers have developed a generative AI framework to create novel motifs for traditional Ulos textiles, a cultural heritage of the Batak people in North Sumatra, Indonesia. By fine-tuning Protogen v3.4 and Stable Dif…
-
New cyclic denoising attack reveals "ultrastable memories" in diffusion models
Researchers have developed a new technique called cyclic denoising to probe image diffusion models for memorized training data. This method involves repeatedly applying forward and reverse diffusion processes at control…