Image created with OpenAI GPT-Image-1. Image prompt: over-the-top 1990s pro-wrestling promo poster, instant-camera ramp featuring “Image Impact” snapping a flashbulb before clotheslining with a film strip; polaroid confetti, grainy print texture, vivid neon titles
RT @OfficialLoganK: Imagen 4 Ultra is the best text to image model in the world 🖼️, and we are just getting started : ) Available right n…”” / X https://x.com/sedielem/status/1948838043236139164
There are prompt injections everywhere for those with AIs to see”” / X https://x.com/goodside/status/1948583404888350780
OpenAI CEO Sam Altman warns of an AI ‘fraud crisis’ | CNN Business https://edition.cnn.com/2025/07/22/tech/openai-sam-altman-fraud-crisis
DrafterBench shows top LLMs still stumble on basic drawing edits, scoring roughly 80 rather than 100. The benchmark targets the everyday pain of engineers who now fix PDF plans by hand. The study builds a 1920‑task suite covering 12 edit types across text, tables, and vectors. https://x.com/rohanpaul_ai/status/1946907944773443888
This Midjourney paper show adding a small video world model at test time lets a frozen vision language model imagine extra views and lift spatial reasoning accuracy about 8% with zero retraining. Most vision language models can name objects in 1 picture, but they struggle to https://x.com/rohanpaul_ai/status/1946472577364545832
Creative upscaling ftw! Turn high altitude aerial photogrammetry into low altitude drone imagery. Such a cool way to frame the shots you want in Google Earth and use a FLUX Kontext LoRA to take it all the way. https://x.com/bilawalsidhu/status/1948035585618427953
🖼️ Bytedance’s Seedream 3.0 is in the Arena! Tied at #4 with top Text-to-Image models: – Flux 1 Kontext Max & Pro @bfl_ml – Imagen 3.0 Generate @googledeepmind Let’s see how it does with a few use cases 👇🧵 https://x.com/lmarena_ai/status/1947341726534013391
Google Photos adds new AI tools including Photo to Video and Remix https://blog.google/products/photos/photo-to-video-remix-create-tab/
🚀 We’ve just released HiDream-E1.1 — an upgrade to our 17B-parameter HiDream-E1-Full model! ✅ Now supports direct commands & flexible aspect ratios 📈 Outperforms open-weight models like FLUX.1 Kontext [dev] in image editing 🔓 MIT License — fully open for commercial use 🔗”” / X https://x.com/vivago_ai/status/1947849390468829418
Fast LoRA inference for Flux with Diffusers and PEFT 🚨 There are great materials that demonstrate how to optimize inference for popular image generation models, such as Flux. However, very few cover how to serve LoRAs fast, despite LoRAs being an inseparable part of their https://x.com/RisingSayak/status/1948403975440793942
The new OpenAI editing update is incredible, so I made a little app to try it out. Just enter your API keys and you’re good to go. You can create or edit any image. I love having this saved on my home screen so I can use it on the go. https://x.com/skirano/status/1946642722430804413
Reconstruct, Inpaint, Finetune: Dynamic Novel-view Synthesis from Monocular Videos”” TL;DR : Video diffusion model for dynamic novel-view synthesis trained in a self-supervised manner using only 2D videos. Novel-view synthesis as a structured inpainting task: (2/3) https://x.com/Almorgand/status/1947265806288515448
Elements for Image to Video generation gets a major upgrade — big improvements in subject consistency, dynamics, prompt adherence, and visual rendering quality! Time to build your scene with Elements! https://x.com/Kling_ai/status/1948610721031549432
