Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

I built a visual reference finder with Jev One single prompt → 100 images from Cosmos, NASA, and The Met my new rabbit hole for creative work 🌻

Albiona Hoti

10,555 subscribers

50,672 views • 2 days ago •via X (Twitter)

Arts Science & Technology

Anya Rossi• Live Now

Private livecam show

24 Comments

Eduardo2 days ago

really cool! lmk if you host that. also interested in how exactly you "prompted" jev. also how is it processing the images? through metadata? or does it actually receive the images as inputs?

Albiona Hoti2 days ago

metadata yes, for custom prompts I send structured choice questions: the brief + styles go in state, and my code supplies possible search phrases. Jev chooses one per source the app searches NASA and The Met’s APIs plus Cosmos’s public search page in parallel, then streams the images into the UI will share the link tomo

Carlo Edoardo Ferraris2 days ago

Did you just casually murder Pinterest? Can you put it online?

Albiona Hoti2 days ago

not trying to murder Pinterest 😅 you can run it here: repo: preview (no Jev): hosted preview is gallery + search only

Yaseen Ammaar2 days ago

jev supports image processing?

Daniel W. Chen2 days ago

Looks cool! what does this do?

Albiona Hoti2 days ago

I send the brief + styles as stated, and my code gives it a list of search phrases Jev picks one phrase per source, then the app queries Cosmos, NASA, and The Met Jev reads titles and descriptions and can highlight one ref per source; my code fetches the images

Daniel W. Chen2 days ago

Thanks for sharing, very creative!!

Atta 🐬2 days ago

one prompt to 100 images is a good use for it.

Albiona Hoti2 days ago

100%, love it for my short form video brolls

Matt Robinson2 days ago

Very cool.

Albiona Hoti2 days ago

thank u

timour kosters2 days ago

Wow so beautiful!

Albiona Hoti2 days ago

🫶🫶

Wyls𖤓n2 days ago

Integrating

eni 🍞2 days ago

that's really really cool!! Did you pre-fetch all data before?

Dr. Xi Zeng2 days ago

Can you open the original museum page from an image on the board?

Albiona Hoti2 days ago

yes, try it here (same for @NASA resources):

Xavi2 days ago

interesting one

Albiona Hoti2 days ago

🙌

R. 👨🏼‍💻2 days ago

is it actually "looking" at the images to classify or just metadata?

Albiona Hoti2 days ago

metadata, it chooses search phrases, then reads titles + descriptions to highlight refs, my code pulls the pictures

R. 👨🏼‍💻2 days ago

ahh sweet

Michael Waitze2 days ago

That sounds like an incredible way to use it for creative workflows. We actually went deeper on this here:

Related Videos

Build an app from a single prompt and publish it on its own domain. Available with SuperGrok Heavy. $100/month for the first 3 months. Here's one I built:

Build an app from a single prompt and publish it on its own domain. Available with SuperGrok Heavy. $100/month for the first 3 months. Here's one I built:

tetsuo

29,675 views • 1 month ago

Everyone's testing GPT 5.6. We gave it superpowers ⚡️ Can your agent generate images, turn them into video, and stitch the whole thing together in one chat? Ours can. The new GPT 5.6 image model is a perfect match for the Sogni Creative Agent. 10 images from a single prompt. One follow-up and they're animated and cut into a finished film. Zero editing apps. The newest models, built in: Seedance 4K + Mini, Krea 2 Turbo, HappyHorse 1.1 and more. Works with any AI agent you already use. One command: npx setup-sogni-agent-skill Sogni Creative Agent. Link below 👇

Everyone's testing GPT 5.6. We gave it superpowers ⚡️ Can your agent generate images, turn them into video, and stitch the whole thing together in one chat? Ours can. The new GPT 5.6 image model is a perfect match for the Sogni Creative Agent. 10 images from a single prompt. One follow-up and they're animated and cut into a finished film. Zero editing apps. The newest models, built in: Seedance 4K + Mini, Krea 2 Turbo, HappyHorse 1.1 and more. Works with any AI agent you already use. One command: npx setup-sogni-agent-skill Sogni Creative Agent. Link below 👇

Sogni.ai

353,235 views • 2 months ago

1/2 Meet Wan2.7-Video — The Comprehensive Model for Controllable Video Storytelling! From single clips to full-scale narrative direction, we’ve built more than just a generator. We’ve built a director’s suite: • Multimodal control over performance and style via text, image, audio, and video. • Character customization with up to 5 reference inputs and voice profiles. • Video editing with simple, intuitive instructions. • Full-stack creative toolkit: generation, editing, cloning, restyling, continuation, and more. • Sustained improvements in visual fidelity, motion stability, and prompt adherence.

1/2 Meet Wan2.7-Video — The Comprehensive Model for Controllable Video Storytelling! From single clips to full-scale narrative direction, we’ve built more than just a generator. We’ve built a director’s suite: • Multimodal control over performance and style via text, image, audio, and video. • Character customization with up to 5 reference inputs and voice profiles. • Video editing with simple, intuitive instructions. • Full-stack creative toolkit: generation, editing, cloning, restyling, continuation, and more. • Sustained improvements in visual fidelity, motion stability, and prompt adherence.

Wan

25,572,948 views • 5 months ago

the most powerful image agent has arrived. flowith image agent doesn’t just make better images. It builds perfect visual workflows. - zoom-worthy details - text that actually works - search-aware creative intelligence - images to videos with seedance 2.0 from one prompt to a complete campaign workflow. like, comment, and retweet for 20 random membership drops!

the most powerful image agent has arrived. flowith image agent doesn’t just make better images. It builds perfect visual workflows. - zoom-worthy details - text that actually works - search-aware creative intelligence - images to videos with seedance 2.0 from one prompt to a complete campaign workflow. like, comment, and retweet for 20 random membership drops!

Flowith

24,733 views • 4 months ago

Bolt built this entire landing page from a single prompt 🤯 No Figma. No coding. Just one prompt and a clear flow Want the exact prompt I used? RT and follow. I’ll DM you the link directly.

Bolt built this entire landing page from a single prompt 🤯 No Figma. No coding. Just one prompt and a clear flow Want the exact prompt I used? RT and follow. I’ll DM you the link directly.

Prajwal Tomar

63,473 views • 1 year ago

Seeing all the insane consistent assets people are dropping with GPT Image 2.0 I built Presets so you can easily copy the prompt masters You (or someone better) nail the perfect prompt + reference images once Then anyone can load that exact setup with one click Out now in SpriteCook (for free):

Seeing all the insane consistent assets people are dropping with GPT Image 2.0 I built Presets so you can easily copy the prompt masters You (or someone better) nail the perfect prompt + reference images once Then anyone can load that exact setup with one click Out now in SpriteCook (for free):

Kimo

23,887 views • 4 months ago

I’m taking part in CRE[AI]TE, CapCut’s global AI Festival. This is my piece for the Creative Track — for experimental visual work built around a clear idea and strong visual hook. $200K prize pool across Film, Series, Creative, and Commercial. Submissions are open until August 10 CapCut

I’m taking part in CRE[AI]TE, CapCut’s global AI Festival. This is my piece for the Creative Track — for experimental visual work built around a clear idea and strong visual hook. $200K prize pool across Film, Series, Creative, and Commercial. Submissions are open until August 10 CapCut

doopiidoo

1,440,788 views • 2 months ago

Ever wonder how creative work happens at OptimAI? Great creative work doesn't begin with a single prompt. It evolves through research, exploration, writing, design, and iteration. That's why we're building OptimAI Creative Studio. A collaborative workspace where specialized Creative Agents support every stage of the creative process - from exploration to production. Coming in early August. ✨

Ever wonder how creative work happens at OptimAI? Great creative work doesn't begin with a single prompt. It evolves through research, exploration, writing, design, and iteration. That's why we're building OptimAI Creative Studio. A collaborative workspace where specialized Creative Agents support every stage of the creative process - from exploration to production. Coming in early August. ✨

OptimAI Network

27,172 views • 1 month ago

A single 2D image → a 110,745-triangle 3D monster with 27 animations, running live in the browser. This is the Abyss Monster, built with img2threejs: The workflow: Image → 3D Reconstruction → Reference GLB + Specs → Rig → Animation Loops → VFX → Interactive Three.js 🔥 Inside this demo: 1/ 110,745 triangles reconstructed from the reference image 2/ 27 animation clips - Spin Flurry, Leap & Stomp, Charge, Collapse & more 3/ Reference-driven rig & animation workflow 4/ Dynamic lighting 5/ Real-time floating ember VFX 6/ Interactive WebGL character What I find most interesting is the workflow itself. The character and scene are built through a multi-prompt workflow, using visual references, GLB specs and animation loops to progressively construct the Three.js experience. Then, for the VFX, I used a single focused prompt to create the floating ember effect and integrate it into the scene. The final result is Three.js + TypeScript code - turning a visual reference into a programmable, interactive web experience. I’ll share the VFX prompt in the comments. 👇 #ThreeJS #WebGL #GameDev #TypeScript #Web3D #img2threejs

A single 2D image → a 110,745-triangle 3D monster with 27 animations, running live in the browser. This is the Abyss Monster, built with img2threejs: The workflow: Image → 3D Reconstruction → Reference GLB + Specs → Rig → Animation Loops → VFX → Interactive Three.js 🔥 Inside this demo: 1/ 110,745 triangles reconstructed from the reference image 2/ 27 animation clips - Spin Flurry, Leap & Stomp, Charge, Collapse & more 3/ Reference-driven rig & animation workflow 4/ Dynamic lighting 5/ Real-time floating ember VFX 6/ Interactive WebGL character What I find most interesting is the workflow itself. The character and scene are built through a multi-prompt workflow, using visual references, GLB specs and animation loops to progressively construct the Three.js experience. Then, for the VFX, I used a single focused prompt to create the floating ember effect and integrate it into the scene. The final result is Three.js + TypeScript code - turning a visual reference into a programmable, interactive web experience. I’ll share the VFX prompt in the comments. 👇 #ThreeJS #WebGL #GameDev #TypeScript #Web3D #img2threejs

Nick

11,377 views • 19 days ago

Kling O1 is GOATED! No Cap! Kling AI -Replace characters with a single reference image or element -Change styles with a video reference and prompt -Add visual FX with ease -Change environments -Quality coherency and outputs from both text and image to video. -So much more! Try it now on OpenArt (Link in the comments! 👇)

Kling O1 is GOATED! No Cap! Kling AI -Replace characters with a single reference image or element -Change styles with a video reference and prompt -Add visual FX with ease -Change environments -Quality coherency and outputs from both text and image to video. -So much more! Try it now on OpenArt (Link in the comments! 👇)

OpenArt

32,119 views • 9 months ago

Seedance 2.5 is now LIVE on OpenGradient! This entire film was generated from a single prompt. One take, no edits. → Up to 30-second clips from one prompt → 10,000 character prompts for full scene-by-scene direction → Up to 30 reference uploads for character and environment consistency → Native audio and sound design built in Even the judges agree: it's a 2.5. Try it now →

Seedance 2.5 is now LIVE on OpenGradient! This entire film was generated from a single prompt. One take, no edits. → Up to 30-second clips from one prompt → 10,000 character prompts for full scene-by-scene direction → Up to 30 reference uploads for character and environment consistency → Native audio and sound design built in Even the judges agree: it's a 2.5. Try it now →

OpenGradient (∇, ∇)

12,051 views • 1 month ago

GPT-4 built a working flappy bird with different difficulty levels from scratch with one single prompt in less than 60 seconds🤯🤯 THE FUTURE IS HERE AND I'M ALL FOR IT!

GPT-4 built a working flappy bird with different difficulty levels from scratch with one single prompt in less than 60 seconds🤯🤯 THE FUTURE IS HERE AND I'M ALL FOR IT!

krish

366,629 views • 3 years ago

Every time I post my GPT-generated images, my DMs and comments get flooded with people asking for prompts. So I built Pinterest, but with the prompts attached. Browse AI-generated images, discover the exact prompts behind them, and use them as a starting point for your own creations. Everything is free to use. Every prompt is fully customizable. Do check out and reply with your fvrt image and create designs using them! Adding new images every week.

Every time I post my GPT-generated images, my DMs and comments get flooded with people asking for prompts. So I built Pinterest, but with the prompts attached. Browse AI-generated images, discover the exact prompts behind them, and use them as a starting point for your own creations. Everything is free to use. Every prompt is fully customizable. Do check out and reply with your fvrt image and create designs using them! Adding new images every week.

Palak

60,822 views • 19 days ago

Creating the content is only half the job. Publishing it shouldn’t become a second workflow. I used Framia to turn a single idea into a complete 20-second cinematic campaign for a fictional energy drink, building the concept, reference assets, individual scenes, and final edit inside one visual workspace. Then came the part I found genuinely useful: Instead of downloading the video, switching platforms, and rebuilding the post manually, I used Social Publisher to publish it directly from Framia. From the first prompt to the finished ad to the live post, the entire creative-to-publishing workflow happened in one place. This is what an all-in-one AI creative workspace should feel like. ✨ Try Framia:

Creating the content is only half the job. Publishing it shouldn’t become a second workflow. I used Framia to turn a single idea into a complete 20-second cinematic campaign for a fictional energy drink, building the concept, reference assets, individual scenes, and final edit inside one visual workspace. Then came the part I found genuinely useful: Instead of downloading the video, switching platforms, and rebuilding the post manually, I used Social Publisher to publish it directly from Framia. From the first prompt to the finished ad to the live post, the entire creative-to-publishing workflow happened in one place. This is what an all-in-one AI creative workspace should feel like. ✨ Try Framia:

Manish Kumar Shah

67,396 views • 21 days ago

This is Flint Image 🔥 Still generating images one by one? Generate four images from a single prompt for 67% less than standard generation. Same quality. More options. One generation. The math speaks for itself. Try it now!

This is Flint Image 🔥 Still generating images one by one? Generate four images from a single prompt for 67% less than standard generation. Same quality. More options. One generation. The math speaks for itself. Try it now!

each::labs

155,348 views • 2 months ago

My first Google Veo 3.1 animated short 🤖 Made from one single image This is Bloom Using Scenebuilder and the New Insert function I was able to extend the scene and prompt new scenes from one hero image.

My first Google Veo 3.1 animated short 🤖 Made from one single image This is Bloom Using Scenebuilder and the New Insert function I was able to extend the scene and prompt new scenes from one hero image.

Dave Clark

167,731 views • 11 months ago

Opus 5 - Music from the first principle This entire song is written by it in codes with visual one shot 50 mins I just want you guys to atleast hear it for 20 seconds you will be hynotised Prompt and code in the comment for future reference

Opus 5 - Music from the first principle This entire song is written by it in codes with visual one shot 50 mins I just want you guys to atleast hear it for 20 seconds you will be hynotised Prompt and code in the comment for future reference

Chetaslua

58,082 views • 1 month ago