开启时会模糊预览图,关闭后正常显示

Author. Coder. CTO. θηριομάχης. Building: https://t.co/otXT4Wy6WR. Writing: https://t.co/dBPBtyCIHw.

~20 yrs in web-dev, now mostly Laravel. My Laravel courses: https://t.co/HRUAJdMRZL My Youtube channel: https://t.co/qPQAkaov2F


I bet you could reproduce this with our models and stuff about Hitler or various slurs etc. I think this has been demonstrated already but maybe I misremember. At any rate, it’s testable. It could also be deliberate sabotage, tho.


Author (Husk, Crypto Confidential): https://t.co/L2COrV5QA3 Building: https://t.co/HMcbuBhTP3 Teaching: https://t.co/Dy0FsZHQaz


Co-founder & CEO @HuggingFace 🤗, the open and collaborative platform for AI builders

关注人工智能、LLM 、 AI 图像视频和设计(Interested in AI, LLM, Stable Diffusion, and design) AIGC 周刊主理人|公众号:歸藏的AI工具箱
