Every week, I organize 400 to 700 links into roughly 60 categories as part of my ongoing effort to learn about AI. This is my personal notebook, which I enjoy sharing with friends… a hobby and a labor of love, rather than a commercial publication or product.
If you arrived here through a search or shared link, this page collects the links I found for Images for the week ending August 21, 2026.
As part of my learning process, I like to automate the category covers. It gives me a chance to learn Python and APIs.
This week’s cover prompt was written using Claude Opus 4.7, and the image was generated using Nano Banana 2.1.
Category Cover Image Prompt: Bright sunlit architectural photograph of a 1929 Los Angeles Art Deco limestone skyscraper seen from across a wide boulevard, perspective-corrected verticals, deep blue sky, with a stylized engaged herm emerging from a pier above the entrance holding a thick carved stone picture frame against its chest containing a simplified Deco limestone relief of a sun, mountains and a palm tree carved from the same honey-cream Indiana limestone as the wall, the word IMAGES incised in tall Art Deco capitals on the lintel directly beneath the figure, dark steel-framed windows, crisp raking shadows, neighboring buildings receding, realistic architectural photography.
This Week in Images News
Summary by Claude Sonnet 5.5 based on this week’s links:
- Image editing leaderboard race: Mustafa Suleyman said Microsoft's MAI-Image-2.5 first hit No.3 on an image-editing benchmark, then claimed the top spot on the Artificial Analysis image-editing leaderboard days later. These are his own claims.
- Practical image tooling: OpenAI said transparent backgrounds are now in preview for GPT-Image-2 in the API, aimed at reusable assets like product imagery and website mockups.
- Image models beyond generation: Skalski showed Qwen3.8-Max doing instance segmentation from an image plus a class list, returning boxes and polygons as JSON. Separately, the PRISM paper describes one diffusion model that generates RGB images and intrinsic maps for relighting and material editing.
This summary was generated by Claude Sonnet 5.5 to help you explore the links below. Rest assured, I select, organize, and check the links by hand in Google Sheets, and write the introduction and personal commentary in The Main Newsletters myself each week as a labor of love.
This week's links related to Images
We hit No.3 on the Image-editing benchmark! … beating Google’s Nano Banana and Meta’s Muse Image models.”
https://x.com/mustafasuleyman/status/2089766508373176726
Transparent backgrounds are now available in preview for GPT-Image-2 in the API. Generate reusable assets you can place on any background… for product imagery, graphic design, website mockups, and marketing campaigns.”
https://x.com/OpenAIDevs/status/2090536933571330440
Qwen3.8-27b is surprisingly usable with codex on my rtx5090! ~200k context with nvfp4 – *very* steerable with skills and plugins – quite smart! great for frontend, basic debugging, and image I don’t trust it (yet) to run in yolo mode – but *very* impressed by how capable it is”
https://x.com/rishdotblog/status/2089458516092399889
things i use codex browser/chrome/computer for – closing the books our accounting software – clearing my linkedin queue – managing gmail / clearing inbox – setting up stripe radar rules – iterating on images in midjourney – browser based QA on every PR – build inspo library from”
https://x.com/clairevo/status/2090147110201291006
Today we’re launching Computer Use for the @TrustVanta Agent. Of the 650,000 images uploaded to Vanta in the past six months, 36% were screenshots because evidence collection outside an API required it. The Vanta Agent can now use a computer to capture screenshots with scoped”
https://x.com/christinacaci/status/2089405423912616073
turns out Qwen3.8-Max can do instance segmentation you send the image plus a class list and ask for JSON (box + closed polygon per object, both in 0-1000 coordinates) we scale those vertices to pixel space and rasterize them into instance masks”
https://x.com/skalskip92/status/2089422495631687759
Qwen3.8 27B as intelligent as Luna Max yoo”
https://x.com/populartourist/status/2089415259199029345/photo/1
Hundreds of 2d photos lifted into 3d. Left exactly when and where they happened at TED. Now I can fly through this spatial memory palace and jump between moments — from the green room to backstage to the main stage. Imagine your entire camera roll coming to life like this.”
https://x.com/bilawalsidhu/status/2090232971320000835
PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling” TL;DR: a unified diffusion model jointly generates RGB images and intrinsic maps, enabling decomposition, conditional generation, relighting, material editing within one foundation model”
https://x.com/Almorgand/status/2090133101028491738
MiniMax H3 image+audio to video feed an audio into h3 instead of generating it. i was testing this flow, got shocked with how good the lipsync and movement is implemented it on the i2v version in diffusers, made a demo for it. what do you think? 🔊 ▶️
https://x.com/multimodalart/status/2089418659370357191
This is super cool! Sota video generation models like our MiniMax H3 understand the movement of a walking character so well, while some people report that latest image generation model still struggles to keep walking motion consistent. MiniMax H3 is here for your game sprites”
https://x.com/MiniMax_AI/status/2089420340728610890
BREAKING: Muse Spark 1.2 by @AIatMeta takes 1st for Video-to-Website with an Elo rating of 1279 and impressive scores across all of our multimodal code categories. Muse Spark 1.2 also takes 2nd for Image-to-HTML with an Elo rating of 1252 and 3rd for Image-to-Frontend with Elo”
https://x.com/DesignArena/status/2090498670685020639
MAI-Image-2.5 is now #1 on the Artificial Analysis leaderboard for image editing! Amazing hillclimbing… compounding the gains!”
https://x.com/mustafasuleyman/status/2090132085562347786
Strawberries. Indoors. Stacked to the ceiling. Now add drones flying between the rows. In the 4D Bios setup, drones move through vertical shelves and capture high-resolution images of leaves and fruit. Instead of manual inspection, plant health becomes a data stream: > drones”
https://x.com/IlirAliu_/status/2089984758486835479
Leave a Reply