Image created with Flux Pro Ultra. Image prompt: A Minecraft screenshot of an art gallery with pixel art hanging on walls and villagers taking photos with item frames used as cameras, with “IMAGES” written in pixelated Minecraft font across the top
“OmniSVG announced on Hugging Face A Unified Scalable Vector Graphics Generation Model https://x.com/_akhaliq/status/1909935266069938653
“@AgentOpsAI 10/ Scaling AI Systems for Human Creativity: Lessons From Building Canva’s AI-First Design Platform Hosted by: Danny Wu, Head of AI Products, Canva This deep dive explores the architecture and strategic challenges behind building accessible AI tools that power millions of” / X https://x.com/AtomSilverman/status/1907898406259011607
“We just built a website using @lovable_dev – and it ended up featured in @FT . Here’s how one designer and one AI tool shipped a live site without writing a single line of code 🧵 https://x.com/davidgaborcom/status/1906282742142087378
“Just built “GhiblitAI” https://x.com/AllAboutJoeX/status/1906539411606827028
“My 5yo drew this today and it melted my heart. It’s not perfect, but it’s full of love and creativity. AI art can be impressive, but it doesn’t have the same soul as a child’s drawing. https://x.com/cto_junior/status/1909877375351111973
“@tkasasagi Edo period cat meme https://x.com/hardmaru/status/1908022570789773516
Our vision for accelerating creativity and productivity with agentic AI | Adobe Blog https://blog.adobe.com/en/publish/2025/04/09/our-vision-for-accelerating-creativity-productivity-with-agentic-ai
“Krea AI just raised $83M in funding from Bain Capital Ventures and others The startup is building a unified browser-based platform that brings together tools to generate, edit, and customize AI-generated images and videos https://x.com/rowancheung/status/1909496835908960312
Krea raises $83M to be the one-stop shop for GenAI creatives | TechCrunch https://techcrunch.com/2025/04/07/kreas-founders-snubbed-postgrad-grants-from-the-king-of-spain-to-build-their-ai-startup-now-its-valued-at-500m/
“A couple years ago, Render, a creative design studio, did a series of famous buildings in alternate styles. I wondered how GPT-4o would be at doing the same. So… first the studio version then GPT-4o with the title as the request Brutalist Louvre & Tudor Sydney Opera House 1/ https://x.com/emollick/status/1909455799698530670
“We’ve made huge improvements to Imagen 3: our highest quality text-to-image model. It’s capable of generating visuals with better detail, richer lighting and fewer distracting artifacts. 🖼️ In #VertexAI, it’s also easier than ever to remove unwanted objects, blemishes, or https://x.com/GoogleDeepMind/status/1910009261075357902
“AI images peaked in 2021 w DALLE-mini https://x.com/nearcyan/status/1910136281813909794
“University of Hong Kong releases Dream 7B (Diffusion reasoning model). Incredibly performant open-source diffusion model. You can adjust the number of diffusion timesteps for speed vs accuracy. – Consistently outperforms existing diffusion language models by a large margin; – https://x.com/rohanpaul_ai/status/1909080035064946998
“🎨 Designers, meet OmniSVG! This new model helps you create professional vector graphics from text/images, generate editable SVGs from icons to detailed characters, convert rasters to vectors, maintain style consistency with references, and integrate into your workflow. https://x.com/fdaudens/status/1910049341571580104
“Discrete diffusion is winning over AR recently: LLaDA-8B, Dream-7B, UniDisc I could be coping but maybe diffusion isnt dead yet UniDisc did comparison and found diffusion model to perform better than autoregressive, as they were ‘less efficient at training time’ but ‘more https://x.com/cloneofsimo/status/1908148670098538645
“Pusa is out on Hugging Face Thousands Timesteps Video Diffusion Model A single model that unlocks: • Text-to-Video • Image-to-Video • Start/End Frames to Video • Video Transitions • Video Extensions • Next-frame prediction • Novel sampling https://x.com/_akhaliq/status/1910350235156488360
“Power to the people: How LLMs flip the script on technology diffusion” / X https://x.com/karpathy/status/1909308143156240538
“So Midjourney users — what are the strengths & weaknesses of v7 you’ve come across so far? https://x.com/bilawalsidhu/status/1908111549824209078
Investing in Krea | Andreessen Horowitz https://a16z.com/announcement/investing-in-krea/
“We’re now beginning the alpha-test phase of our new V7 image Model. It’s our smartest, most beautiful, most coherent model yet. Give it a shot and expect updates every week or two for the next two months. https://x.com/midjourney/status/1908012961840672947
“@AgentOpsAI 9/ Train Video Foundation Models at Scale Hosted by: Ersin Yumer, Sr. Director of AI/ML Platform and Data, Adobe Deep dive into how generative AI is being used to train foundation models at scale. https://x.com/AtomSilverman/status/1907898363313565814
“Very proud to introduce Kaleidoscope ✨🌿 🌍 18 languages (Bengali → Spanish) 📚 14 subjects (Humanities → STEM) 📸 55% requiring image understanding! A very important open science collaboration — which extends in-language evaluation for vision models to many more languages.” / X https://x.com/sarahookr/status/1910340417914384581
“I am a big fan of Midjourney if you want to do visually interesting AI images, and have been using it since 2022. I like their new releases but the problem with the new v7 (right) released today is that v6 (left) was already really good. Experimenting will be fun, though.” / X https://x.com/emollick/status/1908013710704103430
“So, let’s hear those Midjourney v7 reviews. Did they cook? Ngl, doesn’t seem promising…” / X https://x.com/bilawalsidhu/status/1908180816963739774
“700M images across 130M users in a week:” / X https://x.com/gdb/status/1907834289661841632
“GPT-ImgEval A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation https://x.com/_akhaliq/status/1908168924186697965
“Now with GPT-4o a year and a half later. (The prompts are just the punchlines: “Interrupting cow,” etc. Interestingly the better prompt adherence makes them kind of boring compared to less faithful image models) https://x.com/emollick/status/1908738416994295963
“Midjourney released V7, the first major update to its image model in almost a year. It includes: —Improved generation quality —Better prompt adherence —A faster and voice-capable Draft Mode to iterate on ideas —Currently in alpha testing phase https://x.com/rowancheung/status/1909154260912124294
“Been playing with the Android Gemini integration, which lets the AI see through the camera, see the screen, & talk in real time. Very similar to what OpenAI released last year. Gemini taking actions on the phone seems likely soon. Really makes how far Apple AI is behind obvious.” / X https://x.com/emollick/status/1909347280999629265
“Old school creepypasta stories make for good AI images. https://x.com/emollick/status/1909335290289783113
Canva’s Biggest Launch Yet Introduces Visual Suite 2.0 to Redefine Creativity and Productivity https://www.businesswire.com/news/home/20250410082173/en/Canvas-Biggest-Launch-Yet-Introduces-Visual-Suite-2.0-to-Redefine-Creativity-and-Productivity
