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.

✳︎ Launching — JSON Visuals for ChatGPT 50+ unique aesthetic codes, with attribute randomiser to get infinite style combinations. [input image] + [json style code] → 🪄 Link in comments 👇 One of my fav is the Absurd Technology style. Do try out your fav styles and comment •... show more

Rahul Chakraborty

22,007 subscribers

214,505 views • 1 year ago •via X (Twitter)

Education Science & Technology Arts

Anya Rossi• Live Now

Private livecam show

12 Comments

Rahul Chakraborty1 year ago

🔗 Try out → Retexturing is pretty simple – video attached. Check the "How to Prompt" page for more prompting and fusion techniques. The style codes should work in previous free models of GPT (Dall-E) also (but the latest 4o model gives the best results).

Rahul Chakraborty1 year ago

The style codes work really great on 3d images. Some outputs from the raw JSON Base Style codes applied on some real device images

Rahul Chakraborty1 year ago

Site was built using Cursor, Claude 3.7. And a fully functioning read-write database via Notion MCP

Square Deal Recordings & Supplies1 year ago

🌼✨ Add California vibes to your style with our Poppy Embroidered Iron-On Patch! 🌸 Easy to apply and perfect for jackets, bags, or hats. Rep the Golden State today! 🌞 #CaliforniaPoppy #IronOnPatch #DIYFashion

Filipe Soares1 year ago

Doing something similar with , i’m actually doing json in the background. Love your approach Did everything in cursor and had integrated with sanity for the CMS Portion of it

Rahul Chakraborty1 year ago

great. how are the pro sales? i have been thinking about it. no clear answer

David1 year ago

Cool, great way to get people started with JSON styles

Rahul Chakraborty1 year ago

the left one 🥵

Ege1 year ago

amazing bro!

Rahul Chakraborty1 year ago

thanks! would love to see what you come up with.

Howard Chen1 year ago

Very cool and inspiring stuff!

Rahul Chakraborty1 year ago

thanks man!

Related Videos

Today I wanted to try a hybrid style! I mixed 3D, 2D, textured, and flat elements, along with various inspirations! I think it's by mixing things up and developing a true style guide that you discover truly original results! For this, Midjourney remains your best friend for discovering, generating, and merging unique styles! I still need to test this with V8 styles very soon! (However, video models sometimes struggle to keep up with and maintain consistency in a more atypical style; you have to do a lot of experimenting.) #DreaminaCPP

Today I wanted to try a hybrid style! I mixed 3D, 2D, textured, and flat elements, along with various inspirations! I think it's by mixing things up and developing a true style guide that you discover truly original results! For this, Midjourney remains your best friend for discovering, generating, and merging unique styles! I still need to test this with V8 styles very soon! (However, video models sometimes struggle to keep up with and maintain consistency in a more atypical style; you have to do a lot of experimenting.) #DreaminaCPP

Anima

23,190 views • 6 months ago

Ok, so the new Midjourney Style Tuner is here and it's a MASSIVE update. There is so much to unpack, no way I can do it all in one post, but here is an overview. You start by typing in /tune followed by your prompt. MJ will generate a range of sample images (between 16-128) showing different visual styles based on your prompt. Then you choose your favorite images from the sample to generate a unique code you can use to customize the look of future jobs. (link below) So for example, I just tried it with the prompt: 💬 1990s, a photo of a woman dressed in fuzzy velour, shimmering midnight hues reflecting sadness by the lake, a contemporary nightmare on cross-processed film --ar 4:5 --c 4 I selected 10 images, which generated the code zlPhgLCHDXol64kPlwSUzu97. I can then add it to my prompt using --style {code} But it makes more sense if you try it yourself, so try playing around with my Style Tuner for that prompt and generate your own code from your selections: Some quick notes: -You can control the level of style applied by adding the --s parameter to your prompt. -You can combine multiple styles together by separating with a hyphen, i.e --style code1-code2 I will be obsessing over this all day tomorrow and sharing everything I learn along the way. This is an incredible update.

Ok, so the new Midjourney Style Tuner is here and it's a MASSIVE update. There is so much to unpack, no way I can do it all in one post, but here is an overview. You start by typing in /tune followed by your prompt. MJ will generate a range of sample images (between 16-128) showing different visual styles based on your prompt. Then you choose your favorite images from the sample to generate a unique code you can use to customize the look of future jobs. (link below) So for example, I just tried it with the prompt: 💬 1990s, a photo of a woman dressed in fuzzy velour, shimmering midnight hues reflecting sadness by the lake, a contemporary nightmare on cross-processed film --ar 4:5 --c 4 I selected 10 images, which generated the code zlPhgLCHDXol64kPlwSUzu97. I can then add it to my prompt using --style {code} But it makes more sense if you try it yourself, so try playing around with my Style Tuner for that prompt and generate your own code from your selections: Some quick notes: -You can control the level of style applied by adding the --s parameter to your prompt. -You can combine multiple styles together by separating with a hyphen, i.e --style code1-code2 I will be obsessing over this all day tomorrow and sharing everything I learn along the way. This is an incredible update.

Nick St. Pierre

377,975 views • 2 years ago

Built this Pixar-style comedy from the ground up — characters, wardrobe, dialogue, punchline. Made with GPT Image 2 and Seedance 2.5 on Fish Creative 👇 Prompt is in the comments! 🎁 Give it a try yourself? Grab my invite code LVEKVO → and unlock 100 FREE credits to start creating your own AI videos. First 99 people only, don't miss it.

Built this Pixar-style comedy from the ground up — characters, wardrobe, dialogue, punchline. Made with GPT Image 2 and Seedance 2.5 on Fish Creative 👇 Prompt is in the comments! 🎁 Give it a try yourself? Grab my invite code LVEKVO → and unlock 100 FREE credits to start creating your own AI videos. First 99 people only, don't miss it.

Shami

41,923 views • 29 days ago

Pantyhose lover’s dream video...From sheer to opaque, glossy to matte, classic black to bold patterns I’m showing you ALL my favorite styles and shades in one video! Which look is your vibe? Drop your favorite color or style in the comments. and link i bio to see more. #Pantyhose #Tights #Legwear #Fashion #Hosiery 💕

Pantyhose lover’s dream video...From sheer to opaque, glossy to matte, classic black to bold patterns I’m showing you ALL my favorite styles and shades in one video! Which look is your vibe? Drop your favorite color or style in the comments. and link i bio to see more. #Pantyhose #Tights #Legwear #Fashion #Hosiery 💕

Hot Avery

19,085 views • 2 months ago

Here it is the result of my project, Epithet Erased: Prison of Plastic, in a Mario and Luigi video game style! Big thanks to Brendan Blaber for all the help and ressources he added to it! 👇 Credit and full video youtube link is in the comment go check it!👇

Here it is the result of my project, Epithet Erased: Prison of Plastic, in a Mario and Luigi video game style! Big thanks to Brendan Blaber for all the help and ressources he added to it! 👇 Credit and full video youtube link is in the comment go check it!👇

Torro/Freezaol ( Comms slots CLOSED DM open !)

195,824 views • 3 years ago

The FINAL BONKdragon attribute is claimable now❗❗❗ This attribute can be obtained by trading a minimum amount of $50 on Pocket Protector Bot thru Jan. 28th. Use the bot on Telegram and link your Solana Wallet with the /link command🐾 Link to try out PP bot is in the tweet below👇

The FINAL BONKdragon attribute is claimable now❗❗❗ This attribute can be obtained by trading a minimum amount of $50 on Pocket Protector Bot thru Jan. 28th. Use the bot on Telegram and link your Solana Wallet with the /link command🐾 Link to try out PP bot is in the tweet below👇

BONK!!!

368,697 views • 1 year ago

ONE PROMPT IN CHATGPT IMAGE 2 JUST REPLACED AN ENTIRE $5,000-$50,000 BRAND DESIGN TEAM Full brand identity. Colors, typography, logo style, aesthetic. All generated in one single prompt. Here's the exact workflow: Step 1: Paste one prompt asking for a complete brand identity. GPT Image 2 generates everything – color palette, fonts, logo direction, overall visual style. Step 2: Use that output as context for every asset you generate after. Campaign visuals, shop graphics, product mockups, social posts – all stay consistent and on-brand automatically. The result: A full visual identity that looks like a real design team built it. Clean text rendering. Consistent style across every single asset. Design agencies charge $5,000-$50,000 for brand identity work. GPT Image 2 does it in one prompt. The full prompt that makes this work is in the video below. Bookmark this post, you'll want to come back to it.

SCOTTY BEAM

12,023 views • 3 months ago

This week, I’m opening my full style and personalization code vault for Midjourney. - 120+ battle tested codes selected for synergy and worldbuilding potential - 8 bespoke personalization profiles refined over thousands of generations - 20 prompt examples - 500 downloadable image examples - How-to guide - Lifetime updates This is my personal Midjourney toolkit, and after realizing I will NEVER discover all the combos, I’m also opening it up to you. Comment “SIGNAL” below for first access and 50% off when it drops 📡

This week, I’m opening my full style and personalization code vault for Midjourney. - 120+ battle tested codes selected for synergy and worldbuilding potential - 8 bespoke personalization profiles refined over thousands of generations - 20 prompt examples - 500 downloadable image examples - How-to guide - Lifetime updates This is my personal Midjourney toolkit, and after realizing I will NEVER discover all the combos, I’m also opening it up to you. Comment “SIGNAL” below for first access and 50% off when it drops 📡

Echoes of Tomorrow

33,284 views • 1 year ago

From the creators of Fights in Tight Spaces, meet KNIGHTS IN TIGHT SPACES IS OUT NOW! ⚔️.⚔️ With a brutal blend of deckbuilding and turn-based tactics, get strategic and MEDIEVAL.🪓 Recruit fighters to your arsenal, and build a deck for YOUR play style.🃏 WISHLIST NOW. 👇

From the creators of Fights in Tight Spaces, meet KNIGHTS IN TIGHT SPACES IS OUT NOW! ⚔️.⚔️ With a brutal blend of deckbuilding and turn-based tactics, get strategic and MEDIEVAL.🪓 Recruit fighters to your arsenal, and build a deck for YOUR play style.🃏 WISHLIST NOW. 👇

Raw Fury I REGIONS OF RUIN RUNEGATE IS OUT NOW! 🍻

15,985 views • 2 years ago

Very excited for I/O next week! 👀 While we count down the days, I wanted to share one of my favorite Stitch prompts that we just made even better: 📝 Copy/paste your messy resume or portfolio data 🖼️ Attach a profile picture 🎨 Ask Stitch: "Make me a resume website in an 80s retro / nature / steampunk style" Stitch builds the site and automatically crops and styles your photo to perfectly match the aesthetic. Export the HTML, drop it on any host, and you have a standout portfolio in seconds. Try it out and show us what you get! 👇

Stitch by Google

38,132 views • 4 months ago

After playing Hytale a lot, having fun, and doing everything I wanted to do, it's time to get to work! This is the first official iteration of my texture for Hytale! I hope you like it; there's still a lot in work-in-progress, but I hope you can understand the vision I'm aiming for. The goal is to create a more anime-style texture, focusing on a Stardew Valley-like style, with cozy and cute pixel art style. I hope you enjoy my journey! Lots of work ahead! #Hytale #HytalePartner

After playing Hytale a lot, having fun, and doing everything I wanted to do, it's time to get to work! This is the first official iteration of my texture for Hytale! I hope you like it; there's still a lot in work-in-progress, but I hope you can understand the vision I'm aiming for. The goal is to create a more anime-style texture, focusing on a Stardew Valley-like style, with cozy and cute pixel art style. I hope you enjoy my journey! Lots of work ahead! #Hytale #HytalePartner

Hatsuya

54,904 views • 8 months ago

📖 MOST PEOPLE ARE USING SEEDANCE 2.0 JSON WRONGLY AND HERE'S WHY One small JSON change can improve every video you generate Most users write a prompt, generate a video, dislike the result, and start over. The best creators don’t work that way. They use JSON to give Seedance 2.0 a structured set of instructions that defines exactly what should happen in the video. Instead of a single block of text, JSON breaks everything into components: • Character description • Environment • Camera movement • Actions • Timing • Visual style • Scene transitions This makes outputs far more consistent and predictable. Why JSON is powerful: • Better character consistency across scenes • More control over camera movement • Easier to edit individual elements • Reusable templates for future projects • Faster workflow when creating multiple videos • Less randomness and fewer failed generations A simple workflow: 1.Define the goal of the video. 2.Create the main character description. 3.Describe the environment and visual style. 4.Add actions and camera movements. 5.Organize everything into a JSON structure. Example: Character - AI fitness coach Environment - modern gym Action - walking toward camera Camera - slow cinematic push-in Style - realistic, commercial quality Instead of rewriting the entire prompt every time, you can simply modify individual JSON fields and keep the rest unchanged. That’s why advanced Seedance 2.0 users are moving from prompting to system design. The future of AI video isn’t writing better prompts. It’s building reusable production pipelines. 📥Tomorrow I'll show you what's sitting right next to this opportunity. 🔖The pinned post has the complete system. Use it or watch someone else do it first

📖 MOST PEOPLE ARE USING SEEDANCE 2.0 JSON WRONGLY AND HERE'S WHY One small JSON change can improve every video you generate Most users write a prompt, generate a video, dislike the result, and start over. The best creators don’t work that way. They use JSON to give Seedance 2.0 a structured set of instructions that defines exactly what should happen in the video. Instead of a single block of text, JSON breaks everything into components: • Character description • Environment • Camera movement • Actions • Timing • Visual style • Scene transitions This makes outputs far more consistent and predictable. Why JSON is powerful: • Better character consistency across scenes • More control over camera movement • Easier to edit individual elements • Reusable templates for future projects • Faster workflow when creating multiple videos • Less randomness and fewer failed generations A simple workflow: 1.Define the goal of the video. 2.Create the main character description. 3.Describe the environment and visual style. 4.Add actions and camera movements. 5.Organize everything into a JSON structure. Example: Character - AI fitness coach Environment - modern gym Action - walking toward camera Camera - slow cinematic push-in Style - realistic, commercial quality Instead of rewriting the entire prompt every time, you can simply modify individual JSON fields and keep the rest unchanged. That’s why advanced Seedance 2.0 users are moving from prompting to system design. The future of AI video isn’t writing better prompts. It’s building reusable production pipelines. 📥Tomorrow I'll show you what's sitting right next to this opportunity. 🔖The pinned post has the complete system. Use it or watch someone else do it first

Zentrix⌚️

112,210 views • 3 months ago

To all the people out there, calling me a high flyer because I can do flips only see a small part of the picture. I’m a hybrid, I use multiple styles of wrestling striking and movement because I can. I’d love for one of you strong style, MMA, old school too tough to do anything outside the box guys to call me out. I’ll wrestle your style, and beat you because you mistake my passion for movement for unnecessary highspots- be honest with yourself you can’t move like me because you don’t train like me… Or prove me wrong 👊🏼💥

To all the people out there, calling me a high flyer because I can do flips only see a small part of the picture. I’m a hybrid, I use multiple styles of wrestling striking and movement because I can. I’d love for one of you strong style, MMA, old school too tough to do anything outside the box guys to call me out. I’ll wrestle your style, and beat you because you mistake my passion for movement for unnecessary highspots- be honest with yourself you can’t move like me because you don’t train like me… Or prove me wrong 👊🏼💥

John Morrison

275,951 views • 3 years ago

THIS IS HOW A $10K/MONTH PRODUCT CONTENT PIPELINE GETS BUILT FROM 1 REFERENCE IMAGE AND A JSON PROMPT The video is not about "better prompting." It is a very simple cheat code: find an image with the exact lighting, color grade and camera feel you want, make AI reverse-engineer the style into a detailed JSON, then feed that structure into Nano Banana Pro with your own product. That is the part people keep missing. They write vague prompts like “make it realistic” and blame the model when it produces plastic garbage. The better workflow gives the model a style contract before asking for the final image. One reference image becomes the art director. The JSON becomes the brief. Your product becomes the asset dropped into a visual language that already works. This is how a solo operator can sell 20-30 "premium" product shots a week without owning a camera, renting a studio or touching a lighting rig. At $150-$300 per image, that is a $3K -$9K/week offer if you can bring clients. Not guaranteed. But the math is why this workflow matters. The article is the same business model underneath: AI output gets valuable when you stop asking for random generation and start building reusable instructions that copy proven formats. No photographer, no studio, no lighting setup, no retoucher, no 12-round creative call. Just reference, extraction, structure and execution. The prompt does not make the photo look expensive. The stolen style system does.

THIS IS HOW A $10K/MONTH PRODUCT CONTENT PIPELINE GETS BUILT FROM 1 REFERENCE IMAGE AND A JSON PROMPT The video is not about "better prompting." It is a very simple cheat code: find an image with the exact lighting, color grade and camera feel you want, make AI reverse-engineer the style into a detailed JSON, then feed that structure into Nano Banana Pro with your own product. That is the part people keep missing. They write vague prompts like “make it realistic” and blame the model when it produces plastic garbage. The better workflow gives the model a style contract before asking for the final image. One reference image becomes the art director. The JSON becomes the brief. Your product becomes the asset dropped into a visual language that already works. This is how a solo operator can sell 20-30 "premium" product shots a week without owning a camera, renting a studio or touching a lighting rig. At $150-$300 per image, that is a $3K -$9K/week offer if you can bring clients. Not guaranteed. But the math is why this workflow matters. The article is the same business model underneath: AI output gets valuable when you stop asking for random generation and start building reusable instructions that copy proven formats. No photographer, no studio, no lighting setup, no retoucher, no 12-round creative call. Just reference, extraction, structure and execution. The prompt does not make the photo look expensive. The stolen style system does.

Nekt0

14,833 views • 3 months ago

Well this went viral. Seems like we need a better way to visualize agentic traces, especially for people who are not crazy technical enough to diagnose a JSON trace. Here's one UX we're exploring in Kitaru ( - a Tinder-style approach to evaluating your agent traces. You can swipe left and right (and up), and leave notes on what went wrong with a mic. There are so many UX innovations that have not happened yet. Leave more ideas in the comments if you have any 👇

Well this went viral. Seems like we need a better way to visualize agentic traces, especially for people who are not crazy technical enough to diagnose a JSON trace. Here's one UX we're exploring in Kitaru ( - a Tinder-style approach to evaluating your agent traces. You can swipe left and right (and up), and leave notes on what went wrong with a mic. There are so many UX innovations that have not happened yet. Leave more ideas in the comments if you have any 👇

Hamza Tahir

16,184 views • 20 days ago

Introducing FLUX 3. One multi-modal model for Image, Video, Audio and Action-Prediction. Creations are truer to life in every kind of style. FLUX 3 Video is now available in early access (link below). Jointly trained in one unified architecture, our model can be extended to predict actions for robotics. See our work with mimic and Audi in the thread.

Introducing FLUX 3. One multi-modal model for Image, Video, Audio and Action-Prediction. Creations are truer to life in every kind of style. FLUX 3 Video is now available in early access (link below). Jointly trained in one unified architecture, our model can be extended to predict actions for robotics. See our work with mimic and Audi in the thread.

Black Forest Labs

1,214,011 views • 2 months ago

🟧 🤝🥊 Did someone said boxing? 🥊 🤝 🟧 It will be possible with this groundbreaking partnership with BitAvatarz the first-ever 3D non-arbitrary avatars (UNAV) on Bitcoin! We'll bring you an exclusive and unique experience inside the Foxxi Bitverse - an exclusive boxing arena where BitAvatarz holders can battle it out in style! 🥊 🌐 🟧 Drop your Taproot wallet address in the comments for a chance to get whitelisted for Bitmap Studios and gain access to this one-of-a-kind experience. 👇

🟧 🤝🥊 Did someone said boxing? 🥊 🤝 🟧 It will be possible with this groundbreaking partnership with BitAvatarz the first-ever 3D non-arbitrary avatars (UNAV) on Bitcoin! We'll bring you an exclusive and unique experience inside the Foxxi Bitverse - an exclusive boxing arena where BitAvatarz holders can battle it out in style! 🥊 🌐 🟧 Drop your Taproot wallet address in the comments for a chance to get whitelisted for Bitmap Studios and gain access to this one-of-a-kind experience. 👇

JUNGL.

24,139 views • 1 year ago