CURATED VISUAL DISCOVERIES
A curated collection of tools, experiments, skills and workflows for people who enjoy making and exploring visual things.
EXPLORE BY FORMAT
EDITOR'S PICKS
An open-source collection of design skills for AI coding tools, built around a landing-page-design rule set that covers page planning, a full visual system, and the delivery details most generated pages skip.
A GPT-image-2.5 prompt for rendering a full periodic table as a wall of transparent glass showcase boxes, each holding a physical sample of the element — plus the corrections chemists posted underneath.
A detailed prompt for a 24mm wide-angle full-body environmental portrait of an adult Chinese female model catching a travel moment at a seaside bus stop. It pins down the pose, the low angled candid camera position, the composition, the late-afternoon side light and the negative constraints, and ends with a request for a natural, non-staged snapshot rather than a runway look.
A short GPT-Image 2 demo that turns an ordinary portrait into a cinematic rainy-night coffee shop scene. Two samples are shown, one of the same woman seated holding a takeaway cup, one standing with a shoulder bag, both lit by warm streetlamps against a wet pavement and a coffee shopfront with hand-painted signs. The full prompt is referenced in the replies rather than embedded in the post, so this entry captures the visual recipe and the prompt's intent, not the prompt text itself.
An open-source Skill and prompt framework for GPT-Image 2 that generates candid real-life summer portraits of a Korean Instagram-style influencer. It runs on a skeleton of five slots, expression, outfit style, scene, moment and photography technique, backed by thick variable pools, so generation stays inside a defined boundary of randomness instead of being over-controlled into drawing conflicts.
An open-source Chinese portrait-photography skill that reads a set of reference images, extracts their shared visual DNA, and rewrites makeup, wardrobe, scene, lens, pose and lighting as prompts you can still edit.
FRESHLY ADDED
A ChatGPT Image 2.5 prompt that turns an orange-and-white clay cat — pixel sunglasses, studded collar, cigarette in mouth — into a 24-frame stop-motion skateboard loop, delivered as a finished GIF in one shot.
A free gacha-style photo prompt for GPT image 2 that turns "what pose should I strike" into "what just happened": 18 unexpected-moment action cards, each draw rolling 3 sets with random outfit, camera and real-life scene, CCD direct-flash style.
A free image-to-image prompt that turns a photo into an impasto oil-painting art print: the subject stays faithful, the surroundings become a compact hand-painted summer world with palette-knife clouds on warm ivory paper.
A free video prompt that turns a three-panel triptych image into a cinematic anime autumn park clip: the same girl on a bench, walking a leaf-covered path, then holding a red maple leaf as the camera pushes in.
A free fill-in-the-blank prompt for GPT image 2 that renders any [STRUCTURE] as a minimal hand-drawn travel-journal artwork: ink sketch on warm ivory paper, tiny handwritten annotations, muted earthy washes and plenty of blank space.
A free open-source AI-agent skill that turns documents into browser-editable presentations: 12 visual themes, 1020 layouts, per-page control consoles, and one-click export to HTML, PDF and genuinely editable PPTX.
A free image-to-image prompt that turns any landscape photo into a tiny minimalist watercolor-and-ink vignette: the artwork sits small and centered on warm ivory textured paper with generous negative space and a tiny handwritten caption — Japanese travel-sketch stationery aesthetic.
A short style formula rather than a runnable prompt: retro editorial still life built on low-saturation pastel, vintage grain and restrained negative space. Four reference images.
BROWSE TOPICS
