Leon FurzeOct 22, 2023

Hands 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/

Leon FurzeMar 28, 2025

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/

KloudiHubFeb 28

🚀 Google just dropped Nano Banana 2 (Gemini 3.1 Flash Image)

⚡ Pro-level image quality + Flash speed
🎨 Faster ideation, edits, and creative iteration
📈 Big unlock for creators + marketers

This feels like a real workflow shift.
#AI #Gemini #ImageGen

NDFeb 23

#AI #ImageGen

https://petapixel.com/2026/02/23/ai-image-whisperer-detector-debunked/?utm_source=flipboard&utm_medium=activitypub

Posted into AI @ai-nndflip

This AI Image Detector Checks a Global Database of Debunked Pictures

This could be a handy tool for verifying pictures.

PetaPixel
Show threadDr. Fortyseven 🥃 █▓▒░Feb 21

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.)

#aiart #ai #imagegen #disinformation

sayzardFeb 12

Wes 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.

https://x.com/WesRoth/status/2021954950990106709

#grok #grokimagine #imagegen #multimodal

Wes Roth (@WesRoth) on X

You can now upload 3 reference images per prompt in Grok Imagine. This is seriously impressive.

X (formerly Twitter)
sayzardFeb 12

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.

https://x.com/kiyoshi_shin/status/2021894966545723695

#anima #comfyui #imagegen #model

新清士@(生成AI)インディゲーム開発者 (@kiyoshi_shin) on X

ComfyUIと協力して開発されている「Anima」モデルを今更触っているけど。Danbooruタグに最適化してトレーニングされているというけど、IP名回避をしてトレーニングされているよう。 プロンプトが、1枚目が「Gundam」とだけ、2枚目が「Pokemon」とだけ、ロボットもでないし、ピカチュウも出てこない。

X (formerly Twitter)
TywèleJan 28

Does 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

sayzardJan 8

Flowers ☾ (@flowersslop)

작성자는 'nano banan pro' 덕분이라고 추정하며, 사람들은 흔히 보는 'AI 느낌'이 아닌 자연스럽고 작동이 잘 되는 이미지 생성(imagegen) 도구를 선호한다고 지적합니다. 즉, 실용적이고 'AI 룩'에서 벗어난 고품질 이미지 생성 솔루션이 인기를 얻고 있다는 관찰입니다.

https://x.com/flowersslop/status/2008834848241467469

#imagegen #imagegeneration #nanobananpro #generativeai

Flowers ☾ (@flowersslop) on X

@testingcatalog pretty sure mostly because of nano banan pro people love imagegen that just works and doesnt have that AI look that everyone is fed up with

X (formerly Twitter)
sayzardDec 27

Emily (@IamEmily2050)

세로(9:16) 비율의 시네마틱 실사풍 이미지 생성을 위한 프롬프트로, Lucy Heartfilia, Natsu Dragneel, Happy가 Magnolia에서 무대 위를 걷는 장면(무릎 위까지 보이는 Medium Full Shot) 등을 상세히 지시하고 있습니다. 생성형 이미지/프롬프트 작성 사례로, 저작권·모델 활용 관점에서 주의가 필요한 유형입니다.

https://x.com/IamEmily2050/status/2004696977884533025

#generativeai #imagegen #promptengineering #copyright

Emily (@IamEmily2050) on X

{ "intent": { "summary": "Vertical cinematic live-action feature film still of Lucy Heartfilia, Natsu Dragneel, and Happy walking through Magnolia.", }, "frame": { "aspect_ratio": "9:16", "shot_size": "Medium Full Shot (knees up)", "orientation": "Portrait",

X (formerly Twitter)