Mark Gadala-Maria (@markgadala)
GPT-2 Image가 유출됐다는 주장과 함께, 생성 이미지가 이제 더 이상 AI 티가 나지 않을 정도로 자연스러워졌다고 소개했다. Minecraft 스크린샷 같은 예시를 통해 이미지 생성 모델의 품질이 크게 향상됐음을 강조하는 화제성 높은 AI 이미지 기술 소식이다.
Mark Gadala-Maria (@markgadala)
GPT-2 Image가 유출됐다는 주장과 함께, 생성 이미지가 이제 더 이상 AI 티가 나지 않을 정도로 자연스러워졌다고 소개했다. Minecraft 스크린샷 같은 예시를 통해 이미지 생성 모델의 품질이 크게 향상됐음을 강조하는 화제성 높은 AI 이미지 기술 소식이다.
https://winbuzzer.com/2026/03/31/midjourney-revenue-above-200-million-hardware-push-xcxwbn/
Midjourney Revenue Tops $200M as It Eyes Hardware
Luma AI's Uni-1 Beats Google, OpenAI on Image Benchmarks
#AI #Uni1 #GenerativeAI #AIImageGeneration #LumaAI #TextToImage #MultimodalAI #AIImages #CreativeTools #ImageGeneration
The reason why I'm pretty sure many pictures are made with "AI", despite not having the typical obvious errors that are associated with "AI" images, is that it just doesn't seem plausible, a human would have drawn them.
I've seen a lot of "low quality" human art and there is usually a limit to how much effort and time someone is willing to invest for which amount of quality.
Nobody would invest the time it would take to draw such images, if they looked this bad.
https://winbuzzer.com/2026/03/22/adobe-firefly-custom-models-public-beta-creator-trained-ai-xcxwbn/
Adobe Firefly Now Lets Creators Train AI on Their Own Art
#AI #AdobeFirefly #Adobe #GenerativeAI #AIImageGeneration #AIImages #BigTech
A little over 50% of people can recognize #AIImages from real photos: https://zorz.it/xvRTa
#MattGrowcoot #AIGenerated #Microsoft #GenerativeAI #technology #PhotorealisticImages #synthetic #RealPhotos
https://winbuzzer.com/2026/03/12/gemini-embedding-2-unifies-text-images-video-in-one-model-xcxwbn/
Gemini Embedding 2 Unifies Text, Images, Video in One Model
#AI #Google #BigTech #GoogleGemini #EnterpriseAI #MultimodalAI #AISearch #AIAudio #AIVideo #AIImages #GoogleAI #GoogleDeepMind #GeminiEmbedding2