Images 2.6 introduces faster image generation, GIF creation, more precise editing, and new API controls across ChatGPT, Codex, and the API.
Why it matters: A brief release note useful for readers tracking image-generation feature updates across OpenAI products.
ChatGPT now supports animated GIF creation using OpenAI's new Images 2.6 model, rolling out to all ChatGPT and Codex users on web, desktop, and mobile, per The Verge. Users can generate a GIF from a text prompt or uploaded photo, then adjust animation speed or edit individual frames. OpenAI is also releasing API models GPT-Image-2.6 "Flare" for efficiency and "Sunburst" for higher quality, and says users now generate over four billion images per week via ChatGPT and the API.
ChatGPT can now create GIFs from a prompt or an uploaded photo, with options to adjust animation speed, edit individual frames, and share the result. The feature rolls out alongside OpenAI's new Images 2.6 model, which the company says also enables faster image generation and is available to all ChatGPT and Codex users across web, desktop, and mobile. OpenAI also launched GPT-Image-2.6 Flare and Sunburst in its API for faster, higher-quality image generation.
Rivermark is an AI design tool for creatives that follows voice-led sessions, letting users brainstorm out loud while it makes edits such as bolding headlines, laying out type styles, applying palettes, and generating a story version. It reads dragged-in websites, brand guidelines, or Canva templates to stay on-brand, and can turn a content plan into 50 posts in a chosen style. The makers argue that hands-off AI tools make content look generic, and that AI is better used as a lever for one's own creativity and taste.
Caloi AI is an AI-powered calorie counter, food scanner and macro tracker that estimates calories, protein, carbs, fat and fiber from a meal photo, with multi-item plate detection, barcode and nutrition label scanning, and voice or text logging. It emphasizes Indian dishes such as roti, dal, biryani, idli and dosa alongside global cuisines, and includes TDEE, BMR, BMI and macro calculators, custom diet modes, water and weight tracking, and meal memory with streaks. The post notes that AI estimates are a fast baseline based on visible portions and can be edited for precision, and states the app is not a medical device.
Tencent's WeChat Vision team released WeVisOne-VL, an open vision language model in 2B and 4B sizes that handles detection, referring, counting, pointing, OCR, segmentation and alpha matting in one model, with pixel outputs from a 9.6M-parameter decoder so no separate SAM is needed. Built on Qwen3-VL, it is trained with up to 8,192 tokens of context and runs on a single GPU via Transformers or vLLM in BF16. Tencent reports the 4B model scoring 71.3 F1 on Dense200 and 81.8 F1 on RefCOCOg test, while noting a 52.6% rejection rate on PR-Bench.
Face Rater is a tool that generates a visual report from an uploaded photo across nine report styles, including overall image, styling, hair, makeup, jewelry, outfit, personal color and PSL analysis on a 0–8 scale. Each report costs 10 credits, with one-time packs from $10 for 100 credits to $50 for 1,000 credits, and new accounts receive 10 credits for one report. The site states results are AI-generated subjective interpretations rather than verified biometric analysis, and that WaveSpeed retains input files for 7 days while the site keeps technical task information for up to 24 hours.
Flow AI Fx presents itself as a unified AI creative studio offering four generators—Video, Image, Music, and Voice—for turning prompts or reference images into first drafts. It describes a four-step workflow: choose a starting point, pick a format, explore and refine, then audition and export studio-quality files. The page frames the tools as a starting point for exploration rather than a substitute for the user's artistic decisions.
This Show HN post introduces an AI object counter that counts items in uploaded JPG, PNG or WebP photos, marking each detection so users can review the total before trusting it. It offers industry-specific counters (bottles, pills, bricks, logs, coins, livestock and more), a tally sheet with CSV export, and Premium options including bulk audits, PDF reports and shareable team links. The page stresses that counts are drafts based on visible pixels only, so hidden or stacked items may be missed and totals should be reviewed or recounted by hand when reported or paid for.
Clarpex is a browser-based AI photo enhancer that restores blurry, grainy, low-resolution, pixelated or damaged photos, including portraits, product shots, screenshots and old family photos. It offers 10 free daily credits with no account required (Standard costs 2 credits per run, Pro costs 10 purchased credits), supports JPG, PNG and WebP up to 20 MB and 40 megapixels, and includes a before/after comparison slider. Photos are used only to create results and are deleted after 24 hours without an account, or kept in History for 72 hours when signed in.
The author recounts receiving an AI-generated "I Voted" sticker in 2026 that was cluttered and contained garbled text, contrasting it with well-designed stickers from places like South Carolina, Michigan, Kentucky, Albany, Louisiana, and New Orleans, while noting Denton, Texas also uses AI-generated stickers. The piece argues that such small AI annoyances accumulate until AI becomes normalized, and that society is currently negotiating where its AI lines are drawn.
ADKA AI is an advertising generation tool that turns a single product image into UGC-style talking-head videos, cinematic ads, unboxing videos, and full sets of Amazon and Shopify product images, with the AI writing scripts and selecting shot structures automatically. It offers 9 validated video formats and 11 e-commerce image styles, powered by models including ByteDance Seedance, Alibaba Wan, MiniMax Hailuo, OpenAI GPT Image 2/2.5, and Google Nano Banana 2/Pro. Pricing is credit-based with per-generation quotes shown before submission, credits frozen during production and charged only on delivery, and 50 free credits on signup.
Nick A. Bild adapted a probabilistic PCA algorithm to run on a Commodore 64, training a model on about 100 retro-inspired 8x8 binary sprites on a modern computer and then converting the simplified generative logic into BASIC. The C64 generates unique 8x8 sprites fitting the training distribution, which are expanded to 64x64 and displayed, with 94 iterations taking about 20 minutes.
Italian police used an AI platform called SWOADS, developed by IT engineer Salvatore Rapicavoli and in use by the Carabinieri art crime squad since 2023, to flag a painting photographed at the Mercanteinfiera antique fair in October 2024 as a match for a 17th-century painting of Saint Agnese stolen from a church in Sulmona 20 years earlier, despite the original lamb having been painted over with a scroll. According to the BBC, SWOADS has recovered more than 300 large paintings and statues and over 165,000 small objects such as coins, letters and medals, worth over $200 million in total. The Saint Agnese painting was returned to the church, but the thieves have not been apprehended.
Adobe Research and UC San Diego researchers developed EditAgent, which pairs a general-purpose image editor with specialized tools and uses a standard language model to compare parallel candidates using verification data such as close-ups, change maps, and measured brightness and color statistics. In a 600-edit benchmark blind-rated by five professionals, the general-purpose editor Flux-2-Klein-9B failed to produce a usable result 42.7 percent of the time, and specialized tools solved roughly two-thirds of those failures. With verification records, all seven language models tested beat the best fine-tuned evaluation model, with Qwen3.8-27B making a usable pick 81.3 percent of the time versus 74.8 percent for EditScore-72B, though the agent needs about ten times as much compute as a single editor.
A PetaPixel article reports that photo studios are closing as the fashion industry adopts generative AI. The item links to the article and to a Hacker News discussion thread with 4 points and no comments.
Hi3D has launched Hi3D V3.0, an AI 3D generation model built on its proprietary Sparc3D engine, which the company describes as the first commercially available version to reach 2048³ voxel resolution. The update targets geometric detail, structural accuracy and texture output, with texture resolution raised to a maximum of 8K paired with an in-house UV completion algorithm. V3.0 is built into Hi3D's broader browser-based platform, which includes image-to-3D conversion, AI texturing, model splitting with connectors, and conversion of textured models into color regions for multicolor 3D printing.
A link to ansi.studio, described as an ANSI 16-bit art design studio with AI integration, was posted to Hacker News. The submission had 1 point and 0 comments at the time of the data.
Meta has quietly launched Style Sketch, an AI fashion app that builds a virtual closet from Instagram photos or manually added items and suggests outfits from clothes users already own, including virtual try-ons on a model matched to body shape and skin tone. The app is available on iOS and Android in Indonesia, Singapore, and Thailand, and can also generate weather-aware trip packing plans; Meta did not respond to TechCrunch's request for comment.
EarnDraft is a tool for generating written books and coloring books with AI, where users describe their idea, approve an outline, and let AI write chapters and create cover artwork. It includes AI-assisted editing, chapter and page rearrangement, and exports to PDF, EPUB, and DOCX. It starts free with 100 credits, with one-time credit packs ($12 for 100 credits) or a $29/month plan, and credits never expire.
This guide explains the Outstanding Tiny Desk AI trend, inspired by Charlie Wilson's NPR Tiny Desk performance of "Outstanding," in which users upload 1–5 photos of people or pets to be placed into a 15-second vertical 9:16 concert video. It walks through the steps at outstanding-tinydeskai.com: assigning photos to the lead vocals, keys, backup left, backup right, and sax positions, then choosing 480p (50 credits) or 720p (100 credits) and generating the video, which includes the original audio and no watermark. It also offers tips such as using clear, front-facing photos without sunglasses or heavy filters.
A test of two flyer prompts run three times each in Claude Design, Canva, Moda and Grafista found that the first three tools returned one layout per prompt in different colours, while Grafista returned six distinct designs. The article attributes the repetition to how generative models predict the most likely output, and says steering away from it requires a detailed prompt written in a designer's vocabulary. Grafista instead starts each design from a Blueprint, a visual reference, rather than a prompt.
Curate is a free iPhone and iPad app that lets you swipe right to keep or left to delete photos, videos and Live Photos, with nothing deleted until you review and confirm the delete pile. It offers filters for screenshots, screen recordings, selfies and other types, size and date sorting, duplicate grouping with a suggested keeper, and on-device Apple Intelligence suggestions for clutter like blurry shots or receipts. The app requires no account, shows no ads, does no tracking, uses no servers, and states that no data is collected.
Tiny Desk AI is an independent paid service that turns one to three uploaded photos into an approximately 15-second, 9:16, 720p MP4 recreating the "Outstanding" Tiny Desk meme, with photo 1 as the laughing lead singer, photo 2 as the sax soloist and photo 3 as the keyboard player. Packs cost $9.99 for one video, $24.99 for three or $69.99 for ten, with no login or subscription, and photos are deleted within 7 days. The site states it is not affiliated with NPR, Charlie Wilson or The Gap Band, and bars celebrities, politicians, minors and anyone who has not agreed.
Motion Crackers is a curated gallery of AI-generated motion designs, called crackers, together with the prompts that created them. The page lists a long roster of contributing creators.
Dola AI is a browser-based creative studio that combines 2D image compositing, canvas editing, 3D scene blocking, a video timeline and reference boards, letting artists arrange compositions before submitting AI generation jobs. Manual editing and project saving use no generation credits, while AI image, video, audio, object and world generation (including World Labs Marble and Fal integrations) consume credits shown as a quote before submission. The service is built on authorized upstream open-source creative tools with its own accounts and private storage.
Autosomal.ai is a free, no-sign-up face analyzer that lets users upload a selfie or take a photo so AI can estimate their age, gender, and the world regions their face resembles most. The site says analysis takes a second or two and recommends sharp, well-lit, front-facing photos without filters or sunglasses for best results.
EveryGen AI is a browser-based tool that combines image generation (defaulting to GPT Image 2), video generation (defaulting to MiniMax H3 Max Turbo), browser image utilities, and a Gemini 2.5 Flash text-rewriting tool called Humanize AI. It offers annual credit plans from Lite ($179/year for 7,200 credits) to Max ($1,199/year for 96,000 credits), and states it is an independent tool, not an official MiniMax or fal website.
PoseForge is a local-first AI studio that takes one to four identity photos plus a pose reference and generates the same people in a new pose and composition, with controls for camera, lighting, styling, fidelity, and output format. It runs as a single Node.js server with an embedded PGlite database and supports interchangeable engines including Codex CLI, Google Antigravity, ComfyUI, OpenAI, Gemini, Replicate, and fal.ai, plus Higgsfield and Dreamina in Advanced Studio. A read-only static demo is published on GitHub Pages, while generation requires running the app locally.
HypeSeoul is a Show HN project presenting an AI-painted isometric map of Seoul that runs on Seoul time, posted to Hacker News with 1 point and no comments.
This walkthrough of FlashFun.dev shows how RunPod Flash runs dedicated serverless GPUs from pure Python decorators with no Dockerfiles, cutting image generation cost from the 3–4 cents per image charged by hosted APIs like Google Vertex AI to between $0.00033 and $0.002 per image. The app races SDXL Turbo on a 24 GB GPU against Flux.1 Schnell on a 48 GB GPU behind a Cloudflare Worker, D1 and R2 stack, using scale-to-zero, model loading in container __init__, low-step distilled models and async polling to keep costs down. Benchmarks put pure GPU inference at 297ms against 1.1s total wall-clock time, with over 70% of latency spent on queuing, dispatch and base64 serialization.
Just Eat apologised after AI-generated images for restaurants without photos produced bizarre dishes, such as bacon and eggs floating in a glass of cola (a confusion between "soda" and "soda bread") and chips poking out of muffins. A spokesperson said the firm was "in the process of removing" the incorrect images and would stop generating more until the AI was further developed, noting it had been trialling AI-enhanced images. The incident highlights difficulties companies face when using AI to interpret words in a specific context.
The author, who has run a home haunted attraction since 2005, describes encountering low-quality AI art, including an image with the Gemini diamond logo, at his first haunt of the year. He argues AI has spread into haunt flyers, props, projections and merchandise—citing Kennywood, The Darkness, AtmosFX, Knott's Berry Farm and Queen Mary Dark Harbor—and that this undercuts the originality and physical craft that make haunts distinctive, even as non-generative AI is used behind the scenes for prop timing and safety planning.
Canva has released Canva Craft, its first in-house image generation model, which it says can compete with comparable models from Google, OpenAI, ByteDance and Meta. Trained from scratch by Canva Research mainly on millions of design templates, Craft plans composition, proportions and text before generating images at up to 2K resolution across more than 30 aspect ratios, renders text in 55 languages, and supports editable layers via Magic Layers. Canva says Craft placed fourth overall and first in portraits and landscapes on DesignArena, and it is available to all users through Dream Lab and the public API, with MCP integration for chatbots like ChatGPT and Gemini planned for later.
Canva launched Canva Craft, its first image generation model, which uses a two-stage architecture to plan a design before generating an image for greater precision, consistency and control. It generates images at up to 2K resolution in more than 30 aspect ratios and was trained on millions of human-made templates from Canva's content library. Canva Craft is available now globally via Dream Lab, and the company plans to let AI agents connect through the Model Context Protocol and to release Craft-fast and Craft-ultrafast models.
Canva released its first image generation model, Canva Craft, developed by its research team to compete with models from Google, OpenAI, ByteDance, and Meta. The two-stage model plans spatial relationships and visual hierarchy before generating images up to 2K resolution in up to 30 aspect ratios, and was trained on human-designed Canva templates rather than photographs. It is available to all users via the Dream Lab tab and the Canva API, with cost-efficient Craftfast and Craft-ultrafast versions planned.