Robert G

@RealProductGirl I am building a garage

I NEED my feed full of builders. What are you working on right now? I don't care if it's a startup or a weekend side project. If you're building something, I want you on my timeline. Reply and let's connect. 👇

Sizzle reel I made for a new line for Dickies, powered by Seedance 2.0, NB Pro, Kling 3.0

@horacedodd love it! Refreshing to hear that compared to all the other X posts that say they one shotted it first try.

Super detailed timestamped prompts. Midjourney images. Omni reference. Some blended eleven labs sounds. Suno V5 score. Color grading. Was a fun process to get that 30 seconds. More efficient and less expensive than 30 seconds of traditional animation. Traditional and AI workflow combined will be nuclear level💯

Modern Gen AI tools don't replace creators — they allow us to iterate faster. Release things into the wild, test, and see what sticks. 🎯

@mxvdxn @yapper_so no gatekeeping the prompts for this

Made with Seedance 2.0 via @yapper_so Beside action, Seedance 2.0 is also very good with candid realism style. And i'm a huge fan of this style.

@InSpatio_AI does it have the ability to show the splat or point cloud view like shown in the beginning of the video?

We don’t generate videos. 🎬 We generate worlds from videos. 🌍 Introducing InSpatio-World — the world's first open-source real-time 4D world model‼️ Your input: a video clip Our output: a dynamic, navigable, persistent world 🕹️ explore freely across viewpoints ⏪ control time forward and backward 🔓 open-source and ready to build on :) Live demo: 🔗 world.inspatio.com Code & weights: 🔗 github.com/inspatio/inspa… Project page: 🔗 inspatio.github.io/inspatio-world

@kkrll_kkrll @kyleanthony excellent. Now ability to upload video and youre cookin

@nsxwolf @kyleanthony yep, made it a bit more evident now

Midjourney to Paper workflow for a new project

@kkrll_kkrll @kyleanthony this is cool, it's stuck on the editing page and can't go back to the filter selector main page. Maybe add filter selector to the editing page plz.

@kyleanthony yep, discovered it's easier to pipeline some effects to fight slopy midjorney output, looks great as the result building this one now to have a bit more control over the effects: thebicycle42.com

@whatsuphabibi90 @socialwithaayan not true, I am using it on Flashboards. look it up on YT

@socialwithaayan What’s the point when Seedance 2.0 can’t be use

🚨 BREAKING: The ultimate prompt library for Seedance 2.0 AI video generation just dropped on GitHub. This repo is the complete collection of high-fidelity, battle-tested prompts for ByteDance's Sora-level video model. You can now generate pro-level videos in seconds using copy-paste prompts for: → Cinematic film styles (Hollywood racing scenes, Denis Villeneuve deserts, Wong Kar-wai rainy nights) → Viral memes and social media shorts (giant cat Godzilla memes, mirror glitches) → Anime and animation sequences (Nezha battles, Van Gogh oil-paint styles, Luffy coding) → Advertising and commercial branding (MUJI promos, perfume animations) → UGC content, short dramas, and wild visual effects (surreal sky zippers, megalophobia) Each prompt includes exact timing, camera moves, character consistency tricks, and motion details that actually deliver. Plus full Seedance API guides and advanced workflows so you can scale it into real projects. No more random guessing. These are sourced from top prompt engineers on X and WeChat and proven to work. Perfect for filmmakers, creators, advertisers, and everyday users who want cinematic AI videos without the headache. 100% free and open source.

@SHL0MS Soul v2 is the closest look to MJ, then edit in NB

i just want something with the prompt control of Nano Banana and the aesthetics of Midjourney is that too much to ask

@craftian_keskin Can you drop prompt you used for this please

AI Advertisement is already here! I think we will wait a while for a high-quality long movie entirely made with AI, but with one reference image, which was made with NBP, you can create an advertisement in seconds with Seedream 2.0. No camera, no model, no lighting. Just prompts.

@Peter_Quadrel AI

NanoBanana 2 just made your static ad agency obsolete. And I just open sourced the entire tool. Drop your product page URL. It pulls your logos, product images, fonts, colors, and brand voice automatically. Builds a full brand guide for you. Then generates ad creatives at scale using nearly 4,000 high-performing ad templates across 8 niches. It dynamically matches the best templates to your brand and brief. Here's what makes it different: → Instant resizing Get any ad in 1x1, 4x5, 9x16 with one click. No regeneration. No broken text. → Highlight-to-edit See an issue? Highlight the area and tell it what to fix. → Multiple brand profiles Run different brands or segments from one tool. → Auto persona building from real customer reviews → Multiple QC loops on briefs and final assets Catches AI-isms before you do. → Upload your own templates or use ours Runs locally. Just needs your Claude and Google API keys. This is the lite version of what we use internally. You get the full finished tool AND the open source code to make it your own. Creatives still design the system, this handles iteration and scale. Want a copy to download? 1. Like this post 2. Comment "AI" Will DM you the tool along with a tutorial shortly after.

@PurzBeats I see that comfy merch how do I get one?

Just riding in a robot car to talk about AI at GDC. The future is weird.

@chatcutapp @Spotify sd 2.0 or a mix?

Watch this first before reading the rest. Done? Everything you just saw in this @Spotify ad, the woman, the music, the motion graphics, was made entirely in ChatCut. I typed in my ideas. That's it. 👇

@ingi_erlingsson @ComfyUI @Alibaba_Wan looks like brandon westgate

By the power of @ComfyUI and @Alibaba_Wan ⚔️🐅

@cfryant honestly soul v2 has the closet mj vibes out of any model right now, and I'm not a fan of higgs either.

Starting to ask myself the same question.

@itspoidaman agree, most are hype bros selling an illusion of having some secret abilities. I think most of these are reasoning models now so it's interpreting no matter the length of prompt

@javilopen So sad, I was so hyped on this model it was supposed to be the answer to all my boring work videos

I would pay and INDECENT amount of money to China just to have a non-nerfed version of Seedance 2.0 🤣

@OVolosin82152 @recraftai it's hard to match the MJ aesthetic. Soul V2 out of all things can get a closer look to MJ for some things, worth testing

I was curious how accurately the Prompt Extract in @recraftai could capture the content of an image. I uploaded three of my images created in Midjourney (the ones on the left), then used the Prompt Extract in @recraftai to regenerate them (the three images on the right). I’d love to hear your thoughts guys, how do you find the result?

@mitch_troy on the other hand you ask Pro to make an invoice as a pdf it says "as an AI I can't make files into pdf's", while gpt just gives you the pdf. Why?

It's pretty underrated that Gemini can just ace minutes of video analysis, and yet the other models don't even take video as an input