ChatGPT's GPT Image 2 is actually incredible. Full visual breakdown of how to fix my desk setup. I refuse to get rid of my second monitor (I need 3 for live zoom client workshops), but this was the kick I needed to manage cables, swap chairs, buy a cabinet. cc @sama @gdb wow
MULTIMODAL AI
-
25 AI Tools: Bots, Video, Images, Slides, Productivity
By
–
25 killer AI tools across the stack Bots: ChatGPT, Claude, Bard/Gemini, Bing AI Video: Runway, HeyGen, Veed, Pictory Images: Midjourney, DALL-E 3, Leonardo, Firefly Slides: Tome, http://
Slides.ai, Decktopus, http://
Beautiful.ai Productivity: Taskade, -
GPT Image 2 Generates Diverse Images for Detailed Prompts
By
–
GPT Image 2 can generate diverse images even for detailed prompts
-
AI Image Generation Limitations: SVG and Scalability Challenges
By
–
Continued weak spots of AI, from the point of view of a business professional and not a PhD biochemist: 1) SVGs. The ability to "illustrate" and have that thing be infinitely scalable. See below image. If you ask for flat PNGs, fine. ChatGPT is the best at the image game right
-
AI Extracts Palm Print and Specular Highlights From Photo
By
–
Bonus, I did not know if this was going to work, but it also outputted my hand print…. prompt: ”Can you also get my palm print extracted from this photo and present the specular highlights of it in black and white”
-
GPT Image-2 Masters Palm Reading With Computer Vision
By
–
You must try this. GPT Image-2 can do PALM reading and I’m so here for it. Full prompt below
-
Image Generators as Vision Foundation Models Through Instruction Tuning
By
–
"Image Generators are Generalist Vision Learners" This paper argues that image generation training acts like vision pretraining. They use light instruction-tuning to turn a pretrained image generator into a generalist vision model. With the key idea being representing vision
-
Xiaomi MiMo V2.5 ASR Models Open Weights Search
By
–
I actually looked for them but didn't find the open weights. I only found their ASR models, which are different? https://
huggingface.co/XiaomiMiMo/MiM
o-V2.5-ASR
… -
Higher Resolution LLM Architecture Gallery and Summaries
By
–
Higher res figures (and summaries) in the LLM architecture gallery:
-
Codex vs gpt-image-2: Quality Differences in Image Generation
By
–
Useful confirmation. Did you find any quality differences between Codex's included image gen and the standalone gpt-image-2 API?