Image created with OpenAI GPT-Image-1. Image prompt: mid‑1990s web‑browser screenshot, CRT glow, 256‑color dithering — JavaScript status‑bar scroller saying “loading…” forever — broken‑image icon gallery caption “AI Images Generator” — crisp pixel edges, screen‑door scan‑lines, phosphor glow
My thoughts on Grok 4 Heavy after 12hrs: Crazy good! “Create an animation of a crowd of people walking to form “Hello world, I am Grok” as camera changes to birds-eye.” And it 1-shotted the *entire* thing. No other model comes close. Watch the full clip. https://x.com/mckaywrigley/status/1943385794414334032
Chat, Brainstorm, and Build Real Business Apps Using Manus AI Agent (Step-by-Step Guide) @ManusAI_HQ agent can turn your prompts into slides, images, videos, and more. ↗️ Quick Read: https://x.com/AIAgentsNewz/status/1939915461900345354
Video game actors’ strike officially ends after AI deal https://www.bbc.com/news/articles/c5ykx117keqo
asked my Video Studio agent to do a pastel cartoon about Vibe Coding 😅 https://x.com/fabianstelzer/status/1942152414036902146
Design systems aren’t just for Figma. I built a full brand & design spec for my Life Calendar hackathon project. Next step: feed it into GPT to generate a token-efficient prompt version to drop into the project prompt in Bolt, so every AI output stays on-brand. See below 👇 https://x.com/cnnrsmth/status/1931044615609581817
ICYMI you can directly use state of the art AI models directly in @code via the Hugging Face MCP server 🔥 In this case I use @bfl_ml Flux to create an image of a Corgi and edit with their latest Flux Kontext – right through your chat! Try it out today at huggingface .co/mcp 🤗 https://x.com/reach_vb/status/1942247029515735263
🚨 Leaderboard Disrupted! A big update for Text-to-Image fans. New models have just landed in the Text-to-Image leaderboard breaking into the Top 10 rankings! Let’s break them down 🧵 💠#2: Imagen 4 Ultra 💠#4: Flux-1 Kontext Max 💠#5: Flux-1 Kontext Pro 💠#7: Ideogram v3 https://x.com/lmarena_ai/status/1942284806550933596
3 new models live in the Arena today 🎇 🧠 Mistral Small 2506: latest 24B open model (Apache-2.0), tuned for efficiency by @MistralAI 🎨 Imagen 4 Ultra: latest text-to-image from @GoogleDeepMind 🖌️ Ideogram v3 Quality: latest text-to-image model from @Ideogram_AI Your votes https://x.com/lmarena_ai/status/1941201546420822489
Kontext-dev by @bfl_ml is number one trending on @huggingface with at least 100 derivative models just a week after release. Let’s go! https://x.com/ClementDelangue/status/1941666556913521109
Built this with @lovable_dev and @midjourney in 10 mins. Design Inspiration @santu_design Checkout second comment to get remix link. https://x.com/Anubhavhing/status/1937752522019749990
i think it might genuinely be over for the average person, there are posts on facebook with tens of thousands of likes about squid game being inspired by real events, with convincing ai generated images the amount of disinformation the average person believes is gonna 100x”” / X https://x.com/qtnx_/status/1942613151633006596
Just In🚨: Manus AI can now Generate Images! @ManusAI_HQ has taken a significant step forward with the introduction of its image generation capabilities, going beyond visuals to understand intent, plan solutions, and integrate seamlessly with other tools for complex tasks. https://x.com/rankAIX/status/1923066112427831372
ByteDance released Tar 1.5B and 7B: image-text in image-text out models 👏 They have an image tokenizer unified with text, and they de-tokenize using either of two models (LLM and diffusion) The model is actually a full LLM (Qwen2), the tokenizer converts image tokens 🤯 https://x.com/mervenoyann/status/1942539723089621055
MedSigLIP: create embeddings for medical images and text – 400M text + 400M vision encoder – Useful for classification, semantic image retrieval, and more -Trained with chest X-rays, CT slices, MRI slices, dermatology images, and more. https://x.com/osanseviero/status/1943584472206549453
