Imisu

Building mascot generator & animator for vibe coders

[Solana @solana]

Bruh

[Imisu @EarlyCallsSol]

@Tamaricsgiely

[Imisu @EarlyCallsSol]

@cryptolyxe Are you moving to the TON chain?

[Imisu @EarlyCallsSol]

@baseddbroo yes?

[Imisu @EarlyCallsSol]

This is not real

Its not GPT images 2

Its not Nano Banana

It was made with viralclones chrome extension

[Imisu @EarlyCallsSol]

@Francis_gw @patrykrx Just use viralclones

[Imisu @EarlyCallsSol]

@patrykrx Or just use viralclones instead of hassling on higgafield

[Imisu @EarlyCallsSol]

@leopardracer yes use viralclones its the best

[Imisu @EarlyCallsSol]

@patrykrx Or just use viralclones

[Imisu @EarlyCallsSol]

Easiest way to clone any video on the internet

Just press generate button

Congrats your ai influencer just got a new video

Try it out! Its called Viralclones

[Imisu @EarlyCallsSol]

@sflorimm bio ai

[Imisu @EarlyCallsSol]

Try creating this with your GPT images 2

Bet you can't

[Imisu @EarlyCallsSol]

One click and the video was cloned

[Model Finder 🧐 @ModelFinderxx]

Would you take her over Sydney Sweeney? (@MarieDeeMelons )

[Imisu @EarlyCallsSol]

No, this wasn't made with GPT images2

it was clones using viralclones chrome extension

How crazy realistic is this...

[Imisu @EarlyCallsSol]

@blueemi99 they gonna drop a banger soon

[Imisu @EarlyCallsSol]

@nicdunz Just use ViralClones at this point

[Imisu @EarlyCallsSol]

Or you can clone any image from the internet without prompting with viralclones

[Miko @Mho_23]

how to generate AI photos that look 100% real with GPT-image-2:

out of the box GPT image 2 has a very noticeable AI look when you don't use references, which is why we are going to be using inspiration photos for color grading and creative direction

> go on pinterest and grab any photo you like that has the aesthetic you want

> upload that pinterest photo into claude opus 4.7 and ask for this:

"analyze this photo and give me a very detailed json prompt that can recreate it, it should be very detailed, really make sure to break down the color grading and all the exact colors in the photo"

the reason we're using claude opus is because of its very strong visual analysis capabilities + its less lazy than gemini when writing json code

we're not using claude sonnet because it doesn't do actual proper photo analysis, which is important for good json with this method

> take the json prompt claude gives you and put it into ChatGPT

> upload your product image and prompt: "using this json as reference, generate a person holding my product [attach product image]"

> GPT-images-2 generates the photo with that person holding your product

you will notice the photo looks more realistic than usual and the color grading will be really good

> save that generated character photo as your reference

> for future generations, attach the character photo each time for facial consistency

now you have a consistent ugc model that can hold different products across multiple photos

you can also iterate the base json prompt and chat back and foruth with claude to create a json prompt based on what you want, then repeat the same process..

i like this because it makes the color grading really good in the photo

the #1 sign a photo is generated with chatgpt is the basic colours and grainy look, but with this method it removes that

this is how you can build a library of high quality ugc content without hiring creators

the json from claude handles the realistic lighting and color grading, images-2 handles the character consistency, and you control the product placement

takes 5 minutes to set up, then you can generate unlimited variations

[Imisu @EarlyCallsSol]

It’s 2026 and GPT Images 2.0 is STILL garbage at generating people 😭

Skin looks straight synthetic, plastic, waxy, dead.

Like a mannequin dipped in Vaseline.

We don’t want to spend hours prompting just to get a decent human.

AI can code apps and write symphonies in seconds but this?

Embarrassing, OpenAI 📷

[Imisu @EarlyCallsSol]

@WaywardDjango @patrykrx grab it on https://t.co/Z5Iyjb7zdL

[Imisu @EarlyCallsSol]

@WaywardDjango @patrykrx its a chrome extension that makes "generate" button on every video/images so you can just press it and clone the image for you ai model