Image created with Ideogram v3. Image prompt: Late‑90s boy‑band cover “Pixel Passion”: members holding oversized instant camera, mosaic backdrop; holographic bomber jackets; cyan‑magenta light leaks, chrome title.
“Runway references is the first one shot tool I’ve seen, that can replicate a likeness accurately and get close to lora quality. It can also use multiple reference images and you can view a scene from another angle. 1st shot here is ref and others are generated. Of course, once https://x.com/TomLikesRobots/status/1916783390252007908
“Today we are releasing Gen-4 References to all paid plans. Now anyone can generate consistent characters, locations and more. With References, you can use photos, generated images, 3D models or selfies to place yourself or others into any scene you can imagine. More examples https://x.com/runwayml/status/1917628723903463526
“You can transform any document into LLM-ready formats using MegaParse. > PDF, Powerpoint, Word > Tables, TOC, Headers, Footers, Images Fully open-source python library. https://x.com/LiorOnAI/status/1915792212157407385
“Introducing Blazingly Fast LoRA powered by @FAL and Hugging Face Providers! 🔥 Bring any compatible LoRA and get generations at lightning fast speeds! ⚡ Lots more to come soon! https://x.com/reach_vb/status/1916803002322559444
“GPT Image Generation Try the latest image generation model from OpenAI that supports contextual image generation and editing. https://x.com/perplexity_ai/status/1915819619333640647
“New image gen model in the API!” / X https://x.com/gdb/status/1915281868066639989
“OpenAI launched gpt-image-1, the AI behind ChatGPT’s viral image gen, in the API The move allows devs to add high-quality image creation, text, and editing features to third-party apps Priced at $10/1M tokens for input images and $40/1M for output https://x.com/rowancheung/status/1915288383091286331
Augment Code on X: “From pixels to production. Using MCP in Agent to go from Figma config to production-ready components — automatically. Watch the demo👇 https://t.co/cyb7rSr9fU” / X
https://x.com/augmentcode/status/1914749626986512785
“Started with a Simple Idea : Upload your photo → Add a tag → Get a circular profile banner. Like LinkedIn’s #OpenToWork tag, but spiritual. 🛠️ Built in <5 hrs using @Lovable + Cursor 📦 100% frontend — no server, no uploads 📱 Mobile-first & privacy-friendly https://x.com/Gautam__Jain/status/1910614389486473320
“Claude Desktop and MCP clients can now generate images and videos using Luma. Meet the Luma API MCP, powered by Photon & Ray. https://x.com/LumaLabsAI/status/1914525883584668067
“you can generate images on perplexity now. the UI is cute and fun. we have also added support for grok 3 and o4-mini for model selection options (which already supports gemini 2.5 pro, claude 3.7, perplexity sonar, gpt-4.1, deepseek r1 1776), and looking into supporting o3 as https://x.com/AravSrinivas/status/1915820052571689245
“Generative AI is cool and all, but SDF modeling just hits different. Non-destructive shaping, blending and boolean modeling on an iPad using Uniform 1.4 https://x.com/bilawalsidhu/status/1915901879147544815
“Baidu dropped faster and cheaper ERNIE 4.5 Turbo and X1 Turbo models 4.5 Turbo, with upgraded multimodality, costs 11c and 44c per million I/O tokens (0.2% of GPT-4.5). X1 Turbo comes at 14c/55c per million I/O tokens, topping DeepSeek R1 and V3 https://x.com/rowancheung/status/1916726621634970027
Figma’s 2025 AI report: Perspectives From Designers and Developers | Figma Blog https://www.figma.com/blog/figma-2025-ai-report-perspectives/
Gemini app now lets you edit images directly https://blog.google/products/gemini/image-editing/
“Native image editing with Gemini is now starting to roll out to all users in the @GeminiApp!! https://x.com/OfficialLoganK/status/1917727175488463014
THUDM/CogView4-6B · Hugging Face https://huggingface.co/THUDM/CogView4-6B
“I built a full web app with 0 lines of code using @v0 by @vercel — and it actually works! Drop in your .txt, .md, .pdf, or images → Get Smart Notes → Turn them into Docs & MindMaps → Even post to social media Try it out here https://x.com/thelapyae/status/1912731312710119523
“10B parameter DiT trained on 80M images, all owned by @freepik . Model commercially usable, raw model without distillation, open sourced. Proud to demonstrate first model-training project with our client @freepik: “F-Lite”, from @FAL https://x.com/cloneofsimo/status/1917244092544847914
“Excited to release ReflectionFlow — a framework that enables text-to-image diffusion models to refine their own output through reflection 💬🔥 We release GenRef-1M, a large-scale dataset consisting of (good_img, bad_img, reflection) triplets. Through extensive experiments, we https://x.com/RisingSayak/status/1915338106510905767
“Dreamina AI has officially launched Seedream 3.0 – its cutting-edge new model. The wait is over！ This is the latest breakthrough in AI image generation. With Seedream 3.0, Dreamina AI delivers: 🎬 Cinematic-quality visuals 🖼️ 2K resolution output 💎 Ultra-realistic textures & https://x.com/dreamina_ai/status/1914683899671875972
Narrator: NO. “Built this in @lovable_dev with new OpenAI image generation api last night. Should I add a paywall and monetize? https://x.com/sethjkramer/status/1915396414244372985
“Figma is leveraging gpt-image-1 to generate and edit images from simple prompts, enabling designers to rapidly explore ideas and iterate visually directly in Figma. https://x.com/OpenAIDevs/status/1915097075722899818
“🖼️ GPT-Image-1 and all the top text-to-image models are now live on LMArena Beta! For now, it only supports single-turn, try it out and explore our new design! https://x.com/lmarena_ai/status/1917327293116264658
Adobe and Figma tools are getting ChatGPT’s upgraded image generation model | The Verge https://www.theverge.com/news/654561/openai-chatgpt-image-generation-model-adobe-figma
“Adobe’s creative tools, including its Firefly and Express apps, will integrate gpt-image-1, giving creators the choice and flexibility to experiment with different aesthetic styles. https://x.com/OpenAIDevs/status/1915097073743008241
“ByteDance’s Dreamina AI officially launched Seedream 3.0, a new text-to-image model —Produces 2K cinematic visuals with realistic textures —Delivers precise typography — #2 on Artificial Analysis’ Image Arena behind only GPT-4o https://x.com/rowancheung/status/1915288450187645016
“Fuck it, starting today you can run inference across 30,000+ Flux and SDXL LoRAs on the Hugging Face Hub via Inference Providers (powered by @FAL ⚡) And.. it gets better, you can generate over 40+ images in less than A DOLLAR! Go try it now on your favourite LoRA on HF 🤗 https://x.com/reach_vb/status/1915830938438717777
“Meta released Llama Guard 4 and new Prompt Guard 2 models 🔥 Llama Guard 4 is a new model to filter model inputs/outputs both text-only and image 🛡️ use it before and after LLMs/VLMs! Prompt Guard 2 22M & 86M are smol models to prevent model jailbreaks and prompt injections ⚔ https://x.com/mervenoyann/status/1917503204826255730
“Don’t sleep on this! 🔥 @Meta dropped swiss army knives for vision with A2.0 license ❤️ > image/video encoders for vision language and spatial understanding (object detection etc) > VLM outperforms InternVL3 and Qwen2.5VL 🔥 > Gigantic video and image datasets 👏 https://x.com/mervenoyann/status/1915723394701467909
“Perception Encoder (PE) Core is a new state-of-the-art family of vision encoders that can be aligned for both vision-language and spatial tasks 👏 For zero-shot image tasks, it outperforms latest sota SigLIP2 🔥 https://x.com/mervenoyann/status/1915723399642435634
“The way that o3 can guess locations feels very science fictional, down to the “zoom, enhance” tools it applies to an image. This is sped up, but it guessed the location from a photo I just took with geodata removed and no clear signage drawing on the vegetation & highway columns https://x.com/emollick/status/1917713929926566179
“OpenAI dropped gpt-image-1 in the API, the model behind ChatGPT’s viral image gen This allows devs to integrate image creation, with text rendering and editing features, into third-party apps Companies like Adobe and Figma are already using it https://x.com/adcock_brett/status/1916523517522087939
“Now that the Studio Ghibli trend is over, I have a suggestion. https://x.com/emollick/status/1916694044807201124
[2502.15436v1] Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning https://arxiv.org/abs/2502.15436v1
