Zeitgeisty Aphorisms
NDhttps://www.geeky-gadgets.com/midjourney-8/?utm_source=flipboard&utm_medium=activitypub
Posted into AI @ai-nndflip
Leon FurzeHands on with DALL E-3: In conversation with… an image generator
This post is part of a series exploring multimodal generative AI (GAI) technologies from text, to image, to audio and video generation. Check out some of the other posts in this series: Hands on with Adobe Firefly: Finally an image generator that can be used in school Hands on with AI audio generation: GAI voice, music, and sound effects Hands on with chat + search: connecting generative AI to the internet Hands on with Bing Image Creator: Microsoft’s image generator just got […]https://leonfurze.com/2023/10/23/hands-on-with-dall-e-3-in-conversation-with-an-image-generator/
OpenAI Has Improved Its Image Gen – But Do We Need More “Offensive” AI?
OpenAI's recent updates to DALL-E 3 aim to enhance its image generation capabilities, but the focus on relaxing restrictions for "offensive" content raises concerns. The integration of more violent and explicit imagery could contribute to misinformation, and doesn't contribute to the future of the technology.https://leonfurze.com/2025/03/28/openai-has-improved-its-image-gen-but-do-we-need-more-offensive-ai/
KloudiHubPosted into AI @ai-nndflip
Dr. Fortyseven 🥃 █▓▒░A month later. Another great model: #Flux2Klein.
Here's some samples with the same prompt. I'll mix up the aspect ratio for some flavor. And maybe tweak the prompt a bit at the end.
(Redundant disclaimer: these are ALL fake.)
sayzardWes Roth (@WesRoth)
Grok Imagine의 기능 업데이트: 이제 프롬프트당 최대 3장의 레퍼런스 이미지를 업로드할 수 있게 되었음. 이미지 기반 참조를 함께 제공해 생성 품질·제어가 향상될 가능성이 있는 중요한 UX/기능 개선입니다.
新清士@(生成AI)インディゲーム開発者 (@kiyoshi_shin)
ComfyUI와 협력해 개발된 'Anima' 모델을 사용해본 소감. Danbooru 태그에 최적화해 훈련되었다고 하나 IP 이름(예: Gundam, Pokemon)을 회피하는 듯한 행동을 보임. 단순 프롬프트로 유사 IP가 생성되지 않아 학습 데이터·정책 관련 특성이 의심된다는 관찰입니다.
TywèleDoes an AI image gen model exist that is transparent in where it sources their data from like Apertus and Starcoder do? These 2 models seem to be the only ones that are completely open and transparent about their weights and training data and remove any data that their owners do not wish to be part of the training data. But they don’t generate images only text or are specialised for coding. I’m curious if there is something similar for images.
#ai #localai #ethicalai #aimodels #apertus #starcoder #imagegen #aiimages