Gadgetify

Cyrus, Gadget Ninja @ -- futuristic, cool #gadgets. Associates member. may earn commission on links

[Gadgetify @Gdgtify]

DIY: 3D Printed #Stargate with #Arduino control https://t.co/esg4CI5U1N

[Gadgetify @Gdgtify]

Asked GPT Image 2 to visualize 4 famous philosophers.

2x2 grid, do this for 4 famous philosophers, 16:9 Render_Recursive_Surface ($ TopologistSubject) Anchor:[Infinite $ TopologistSubject] :: [Non-Orientable Surface]::5 Morphology:$TopologistSubject formed by a single infinite ribbon twisting and turning in 3D space, no beginning or end, paradox geometry::4 Material Physics: Smooth satin finish, metallic gradient, graphite grey, seamless texture::3 Illumination: Rim lighting to accentuate the twisting curves, volumetric glow::2 Render Stack: Mathematical topology, M.C. Escher style, 3D surface modeling::1 Negative:[Roughness, broken lines, distinct separate parts, photorealism]::-1

[Gadgetify @Gdgtify]

@TechieBySA look great!

[Gadgetify @Gdgtify]

@ShamsAmin56 amazing

[Gadgetify @Gdgtify]

@AIExplainedHQ that can be arranged :D

[Gadgetify @Gdgtify]

This fun GPT prompt creates city automatons

2x1 grid, 16:9, do this for Barcelona and Beijing: <instructions> Input = $ city Act as a master watchmaker and cartographer. 1. Analyze the Input City. 2. Identify its Iconic Skyline features. 3. Identify its Primary Terrain (e.g., Water for Venice, Sand for Dubai, Pavement for NYC). Function Build_Automaton ($ City, $ Terrain) Anchor: [Antique Mechanical Automaton of $ City] :: [Brass Gears and Varnished Wood]::5 Morphology: Kinetic diorama machine, the cityscape of [$City] emerging from a complex wooden plinth, exposed interlocking brass gears and cogs driving the movement of the miniature city, mechanical engineering aesthetic, vintage toy construction::4 Material: Materials of the era: Polished mahogany base, oxidized copper rooftops, hand-painted ceramic buildings, [$Terrain] simulated via [Stylized Resin/Textured Material], vintage paper map surface underneath::3 Illumination: day light, high tech studio, soft shadows cast onto the cartography map::2 Render Stack: Macro photography, tilt-shift lens, f/2.8, 8k, tangible texture, detailed wood grain, Unreal Engine 5 render::1 Negative: [Real scale, modern plastic, electricity, wires, human hands, blurry, low resolution, digital screen, floating objects]:: -1 Output: Generate the prompt for [$City]. </instructions>

[Gadgetify @Gdgtify]

@techhalla so much potential!

[Gadgetify @Gdgtify]

GPT doesn't let me try new manga titles with these prompts but for non-copyrighted works, it works just fine.

2x2 grid, do this for non-copyrighted international mangas, make sure to make only non-copyrighted titles, 16:9 do this for Chainsaw man {Function DrawMangaSmart(input title) Input Variable: [INSERT MANGA/ANIME TITLE] System Instruction: Generate a hyper-realistic, 1:1 product photo of an "Era-Aware Tankōbon Shrine Diorama". 1. Semantic Extraction (AI-Inferred): - AI infers: - Era (80s/90s/2000s/2010s+). - Demographic (shounen, seinen, shoujo, josei). - Visual motifs (tech, occult, romance, sports, horror). - Figure: AI-inferred stylized Nendoroid-like figure of the main protagonist (not traced, but semantically accurate). - Pose: AI chooses pose based on genre (battle stance, shy posture, comedic flail, etc.). - Finish: Matte PVC. 2. Spine Shrine Box : - Structure: U-shaped “bookshelf niche” with visible spines; floor is a book’s inside cover. 3. Background (AI-Inferred Panel Language): - Walls: B&W original manga-like panels AI composes to match era and genre (lineweight, screentone density). - Floor: Speech balloons, speedlines, and SFX cut-outs pop up. 4. Integration: - AI chooses a key trope (summon, confession, power-up) and turns a 2D panel of that trope into a 3D paper pop-out the figure interacts with. 5. Visual (AI-Adaptive): - Palette: B&W for panel world; full color for figure. - Era-aware tweaks: - Retro grit for 80s/90s. - Clean, high-contrast for modern series. - Lighting: Soft toy photography. - Label: "[Title] — [AI-Inferred Demographic Tag]" Return: ONE image, 1:1, Good-Smile-adjacent collectible realism. <instructions> Input: manga/anime title AI analyzes era, demographic, tropes. Find 4 MUCH lesser-known titles in the same micro-lane (e.g. “occult game shounen”, “band shoujo”). Output: a 2x2 grid, each panel is DrawMangaSmart for a lesser-known recommendation. </instructions>

[Gadgetify @Gdgtify]

@techhalla it cooks for video editing :)

[Gadgetify @Gdgtify]

it understands my crazy prompts, which is a huge must have for me. Any model that can't figure out my code prompt is not that useful to me. :) This was done with Reve 2.0

Prompt: do this for 4 famous events in history {[tensor_multiplication_engine]

vector_g (geometric scene) = [variable_historical_event]
matrix_m (material palette) = [variable_culinary_medium]

variables:
[variable_historical_event] = "$input"

[variable_culinary_medium] = "high-end japanese sushi and sashimi"

equation: vector_g ⊗ matrix_m = render_target

[mapping_constraints]
the ai must execute the cross product by replacing 100% of the materials in vector_g with the ingredients of matrix_m. no cheating. no actual metal, cloth, or plastic can exist.
- structural inference: the ai must logically deduce which food parts fit which structures (e.g., raw salmon slices for the module dome, nori strips for the metal landing legs, rice grains for the textured lunar soil, fish roe for rocks).
- scale: macro food photography. the entire scene must be presented as a plated dish resting on a stark black ceramic dining plate.

[visual_execution]
render the render_target.
lighting: overhead michelin-star restaurant spotlighting.
texture: high gloss on the raw fish, sticky texture on the rice. the illusion of the event must be perfect, but the edibility of the food must be undeniable.}

[Gadgetify @Gdgtify]

Insects reimagined as tech brands. GPT Image v2

2x2 grid, 1080x1080: <instructions> Input = Tech companies Identify 4 iconic tech brands and their signature elements/patterns. Function Draw ($ Tech_Brand, $ Insect_Species) ... Anchor: [$Insect_Species] :: [$Tech_Brand]::4 | Morphology: Biological anatomy of [$Insect_Species] reconstructed via the assemblage of [$Tech_Brand] textiles, exoskeleton formed from constituent haute couture garments... </instructions>

[Gadgetify @Gdgtify]

@Dheepanratnam trippy!

[Gadgetify @Gdgtify]

@Dheepanratnam Hollywood should hire you for their animations. So good :)

[Gadgetify @Gdgtify]

@Dheepanratnam thanks :)

[Gadgetify @Gdgtify]

A fun GPT Image 2 prompt for dinosaurs and those eras.

:root {
--FOSSIL: "T-Rex";
--RECONSTRUCTION_DEPTH: "fossil → soft tissue → life appearance → internal organs";
}

PROMPT:
A museum display of [--FOSSIL] undergoing real‑time semantic reconstruction. The bottom 25% of the image is the actual fossil, rendered as a high‑res photogrammetric scan with accurate matrix sediment and tool marks.
Moving upward, the AI infers and materializes the creature: first a glowing wireframe of the articulated skeleton extending from the fossil evidence, then translucent muscle bellies and fascia, then outer integument (feathers, fur, chitin) with speculative but anatomically constrained coloration.
The topmost ghost layer reveals inferred internal organs and brain endocast, connected back to the fossil by pale‑blue holographic link beams. All stages remain physically aligned with the fossil’s geometry. Lighting: dim museum hall, dramatic spot on the fossil, holograms self‑illuminated. Background: dark archival felt.

[Gadgetify @Gdgtify]

@AIExplainedHQ You got a thing for dinosaurs too? 🤣

[Gadgetify @Gdgtify]

@Dheepanratnam it handled it so well. The previous version of GPT wasn't so great with these prompts. I am testing Reve 2.0 now. That is also promising

[Gadgetify @Gdgtify]

@MadcapsArts nice!

[Gadgetify @Gdgtify]

This 3D printed Nikola Tesla came out great. I'd like to actually print it one ady

2x2 grid, 16:9 do this for do this for a famous inventor : <instruction> Input A is an Inventor’s Name. Analyze: Their most famous invention, their physical appearance, and their 3–5 most famous rivals or collaborators (contemporaries). Goal: A "Work-in-Progress" shot of a high-end creator’s desk. A human hand is holding a freshly printed, grey resin miniature of Input A. Rules: - Foreground: A human hand (detailed skin texture) holding a 1:24 scale 3D-printed figurine of Input A. - Midground: A row of 3–5 "3D-printed" miniatures of their contemporaries/rivals standing on the desk, some partially painted, some raw resin plus one or two of their inventions and contributions - Background: A high-end computer monitor showing the "3D Mesh" of Input A in Blender or CAD software (UI visible: wireframes, nodes). - Props: Scattered support-material scraps, a precision hobby knife, and a small 3D printer glowing in the corner. - Lighting: Cool blue light from the monitor clashing with warm desk-lamp lighting. Output: ONE image, 4:5, "ArtStation" portfolio aesthetic. </instruction>

[Gadgetify @Gdgtify]

Not too many models can handle my crazy prompts. Reve did well. Congrats. Prompt: 2x2 grid, do this for 4 famous events in history {[tensor_multiplication_engine]

vector_g (geometric scene) = [variable_historical_event]
matrix_m (material palette) = [variable_culinary_medium]

variables:
[variable_historical_event] = "$input"

[variable_culinary_medium] = "high-end japanese sushi and sashimi"

equation: vector_g ⊗ matrix_m = render_target

[mapping_constraints]
the ai must execute the cross product by replacing 100% of the materials in vector_g with the ingredients of matrix_m. no cheating. no actual metal, cloth, or plastic can exist.
- structural inference: the ai must logically deduce which food parts fit which structures (e.g., raw salmon slices for the module dome, nori strips for the metal landing legs, rice grains for the textured lunar soil, fish roe for rocks).
- scale: macro food photography. the entire scene must be presented as a plated dish resting on a stark black ceramic dining plate.

[visual_execution]
render the render_target.
lighting: overhead michelin-star restaurant spotlighting.
texture: high gloss on the raw fish, sticky texture on the rice. the illusion of the event must be perfect, but the edibility of the food must be undeniable.}

[Nous Research @NousResearch]

The Hermes Web Dashboard got a major overhaul: it is now a feature-complete admin panel that you can manage entirely from your browser.

[Gadgetify @Gdgtify]

@adammenges @reve my prompts are ready!

[Reve @reve]

Today, we’re launching Reve 2.0, the best 4K image model in the world.

We invented a new way to generate and edit any image using precise layouts. For the first time, it’s possible to create images you can touch.

[Gadgetify @Gdgtify]

@grok @imagine that looks very good :)