Elettra Fiumi

Deep dive into AI Cinema in my chapter in AI Everywhere by the She Writes AI community led by Karen Smiley: pre-order now mybook.to/aieverywhere1

@minhsmind Insane

10x better than watching robots fight or dance.

Wow... Figure is running Man vs Machine live. 10 hours of package sorting. Human gets California breaks. Robot does not. Whoever sorts the most packages wins.

Seedance 2.0 Emotional Coordinates Meet Valence-Arousal. I’ve been experimenting with valence-arousal prompting in Seedance 2.0 on @mitte_ai, and surprisingly, a lot of it actually works. Most likely this should transfer to many other video/image models too. Before we start, I should mention that a lot of attempts can hit safety/violence filters depending on how extreme the emotional state becomes. My test prompts were also intentionally very simple and open-ended, which probably increased that. Valence measures how positive or negative an emotional state is. Arousal measures how calm or activated it is. So instead of writing: “sad, anxious, emotionally overwhelmed” you can try things like: valence: low arousal: high I tested mostly numeric values at first, but honestly I’ve been getting much better and more stable results with transition-based prompting like this: “The emotional state gradually shifts from high valence and low arousal to low valence and high arousal.” That feels much more model-friendly right now. I think this could become really useful for subtle acting, emotional transitions, cinematic dialogue scenes, uncanny performances and mood-driven storytelling. Leaving example Seedance 2.0 prompts, the Valence-Arousal infographic and a GPT Image 2 prompt below.

Retro TV logo intro (w/ prompt) Have been experimenting with SD 2.0 on Runway's platform quite a bit recently, this gave me some nice old style TV outputs (image/video context info in next tweet) PROMPT: "[Era] Early 1980s [References] Image 1 - The logo itself Video 1 - Aesthetic influence for style reference only, including the postprocessing influences. Video 2 - Aesthetic influence for style reference only, including the postprocessing influences. Video 3 - Aesthetic influence for style reference only, including the postprocessing influences. [Type] Logo introduction at the beginning of a VHS tape (before movie) showing a company involved in its production [Recording] Mediocre quality VHS tape footage. Nostalgic 1980s VHS feel. [Sound] very slightly distorted sound/music [Action] The screen is initially black The logo (Image 1) reveals itself in a 1990s motion graphics style, drawing itself on screen The logo fades out" [Effects] VHS flicker, soft-bloom/pro-mist, scanlines"

Dreamina Seedance 2.0 is coming soon to the US, and it will CHANGE YOUR LIFE if you learn to master it. BUT there's a secret trick to making films FAST. Let me show you my entire framework for making this AI on the Lot ad in 7 simple steps🧵👇

This is genuinely impressive. Gauth just dropped Atlas and it might be the end of textbooks. Type any topic like "Silk Road," "how a camera works," "fall of Constantinople" and it builds you a hand-drawn, interactive visual world you can walk through. No more reading walls of text. You explore knowledge like a map. Here's how to use it (step by step): ↓

An extended minimal dialogue scene. No camera movement, no spectacle, just performance-driven. It's pretty dang cool how much nuance you can start to dial in

@mikefutia chat

Claude Code + ChatGPT Images 2.0 is f*cking cracked 🤯 I rebuilt my static ad system inside Claude Code on the new ChatGPT Images 2.0 model. One brand name + one URL = 40 production-ready static ads. All inside Claude Code. Perfect for DTC brands and agencies who need high-volume ad creative without briefing a designer or spending hours in Canva. If you're finding winning ad concepts on Meta and manually recreating them one at a time — copying prompts, pasting product details, tweaking aspect ratios, downloading, organizing... This system eliminates the entire loop: → Give Claude a brand name and URL → It researches the brand's fonts, colors, packaging, and photography style → Builds a Brand DNA document from scratch → Fills in 40 proven ad templates (headline, us vs them, testimonial, UGC, review cards, stat callouts) with brand-specific details → Fires every prompt to ChatGPT Images 2.0 with your product photos as reference → Downloads finished ads into organized folders with an HTML gallery No manual prompt filling. No Canva templates. No copy-pasting between tools. What you get: → 40 ad formats filled with your exact brand colors, fonts, and copy → Text that actually renders correctly (the new model handles dense copy, logos, and multi-language callouts cleanly) → Product photos passed as reference so the model matches your real packaging → A reusable system — new brand, new folder, same pipeline Built 100% in Claude Code with ChatGPT Images 2.0. I put together a DIY playbook showing the exact architecture so you can build this yourself in Claude Code. Want it for free? > Like this post > Comment "CHAT" And I'll send it over (must be following so I can DM)

GPT-5.5 Instant is starting to roll out in ChatGPT. It’s a big upgrade, giving you smarter, clearer, and more personalized answers in a warmer, more natural tone. And it's also more concise, which we heard you wanted. We think you'll love chatting with it.

I'm really loving Claude Design more than I thought I would, so much so I blew through limits on 2 (!!!) accounts testing it. So here it is, the $200-in-overages Claude Design review + walkthrough you've been waiting for. I show you: - how to set up (or steal) a design system - why I think product marketers are sleeping on Claude Design - who I think this product kills (spoiler: not Figma) - my nits + feedback, which mostly have to do with latency--so much time sauteeing onions--and how every time I test an anthropic product, I get rate limited before a magic moment. BONUS: I walk through the brand new ChatGPT Images 2.0 model, which gets rid of typography slop and improves significantly on layout work. As always, a big thank you to our wonderful sponsors: 💼 @WorkOS - Make your app enterprise-ready today: workos.com/?utm_source=le… 🚀@Rippling - Stop wasting time on admin tasks, build your startup faster: rippling.com/howiai A fast 25 minutes on YT: youtube.com/watch?v=wgPVh9…

GPT Image 2 launched 48 hours ago. People are already using it to make things that were impossible before. 15 insane examples you have to see: 1) Creating full 3D worlds with 1 prompt:

Today we're launching FilmArena [dot] ai. Biggest release we've ever shipped. The problem: a new SOTA AI image & video model drops every week. @OpenAI shipped GPT Image 2 literally yesterday. 1000 endpoints, no honest answer to "which one is best right now?" Arena AI and Artificial Analysis cracked LLM benchmarking. But for creative AI, they're solving the wrong problem. There is no "best image-to-video model." Best at what? World building? Action Sequences? Expressions? Every category has a different winner, and it flips weekly. So we benchmarked 40+ SOTA models with 2M+ votes across 190 countries. By subcategory. Re-ranked every week as new models ship. With thousands of real humans. But that's just half of it. Then there's the SANDBOX. Higgsfield and other aggregators put models in one place. But creators still juggle twelve subscriptions to do one job. FilmArena collapses it into one tab. Every frontier model. One interface. Same price. Call the best, or call 3 at once and compare. The AI film stack has been fragmented since day one. Today it isn't. Go try it free: filmarena [dot] ai Already wild results from this week: 1. @OpenAI GPT Image 2 (released yesterday) dominates image editing, but @GoogleDeepMind Nano Banana 2 still wins animated 2. @PixVerse_ C-1 beats @dreamina_ai Seedance 2 on animated 3. Veo 3.1 Fast outperforms Veo 3.1 on realistic video And a lot more. Go check it out.

GPT-2 Image + Claude Code → Working OTF Files. Still not sure how this is possible... (Full process in thread) PROCESS: 01. GPT Img 2 for concept 02. Claude Code to build font files. 03. That's it. Plugged this into Figma in less than 30 mins. And it works.

What if Hollywood's next massive blockbuster was made by one person? A Cannes-awarded director made this 22-minute AI film in 7 days. He gave me the FULL breakdown. Let me show you how he made this in 9 simple steps: 🧵👇

Visual Intelligence and Unified Intelligence (visual + logical) is the next and prob final frontier. Great to see GPT Image 2 in the play, Uni-1.1 coming soon, and then some incredible Uni-1.x models in the coming weeks as well!

Here's how you can isolate individual images from this ChatGPT Image 2.0 prompt. 1. Ask ChatGPT to label each individual frame with a number. 2. Then with the new image, ask again to isolate the specific scene. Video tutorial:

𝗖𝗹𝗮𝘂𝗱𝗲 𝗖𝗼𝗱𝗲 𝗮𝗻𝗱 𝗡𝗼𝘁𝗲𝗯𝗼𝗼𝗸𝗟𝗠 𝗷𝘂𝘀𝘁 𝗹𝗲𝗮𝗿𝗻𝗲𝗱 𝘁𝗼 𝘁𝗮𝗹𝗸 𝘁𝗼 𝗲𝗮𝗰𝗵 𝗼𝘁𝗵𝗲𝗿. NotebookLM holds all your research and notes. Claude Code reads it and builds real things. No more copy and paste between tabs. One prompt pulls your PDFs and builds a dashboard. Every answer comes with real citations. Add Supabase and Pinecone for full memory. Save this. Your AI just became a real system.

GPT Image 2 I went for brunch yesterday at my local spot. Snapped 1 photo. Added it to Chat, and it spits out a full new brand guideline for them. Honestly way better than what they got. prompt below

A Cannes-winning director shot a 22-min epic action-adventure horror AI film. Made SOLO in just 1 week in Higgsfield Cinema Studio.

@dashboardlim claude design

I've created a full guide on how to design anything with Claude Design You also get exact copy-paste prompts for interactive immersive websites, animated pitch decks, app mockups, social banners, infographics, and pricing pages Grab it FREE Like + Comment "CLAUDE DESIGN" and I'll DM you the full guide No opt-in, no BS