Mark Ledford

GPT Image 2.6 is live on Sogni! And yes, it makes GIFs! Just switch from Image to GIF, and you're good to go. These two sloths were created exactly that way. 🦥 Want more control? You can choose between 2 and 16 frames, with 20 to 2000 ms per frame. Two versions are available: Sunburst and Flare. Besides GIFs, GPT Image 2.6 also supports: - Editing your own reference images - Annotation-based editing: draw directly on an image to show what you want to change - Clear, readable text in images - Planning depth independent of render quality (Low to Maximum) - Transparent PNG and WebP outputs Full breakdown, settings, and pricing here 👇

This hotel doesn't exist. Every room was made up, from the lobby to the pool over the sea. It's a Sogni World, so people move through it by clicking, hit a door and you walk into the next room. Each click plays a short film. Think about what you could build with it for a client: - A hotel that lets guests look around before booking - Apartments that aren't built yet - Wedding venues, rooftop bars, event spaces - A brand launch people actually explore - Museums, cruise ships, whole cities - Ads where the viewer picks where to go Start from your client's photos or just an idea. Links below 👇

MOSS-Image SFT and MOSS-Image 8-Step are now on Sogni, and both are included in Sogni Unlimited It’s OpenMOSS’s 5-billion-parameter text-to-image model, made for text. Quote the words in your prompt and it writes them out exactly, from long instructions and terminal commands to full menus, in English and Chinese. Every image in this thread was made with it 👇🧵

Layout Composer is here on Sogni ☕️ Instead of hoping a prompt puts things in the right spot, you place them yourself. Draw boxes for the cup, the cookie and the headline, and the image follows your layout. Works with MOSS-Image SFT, MOSS-Image 8-Step and FLUX 3 Image Klein 👇🧵

FLUX 3 Klein is now on Sogni, and it's included in Sogni Unlimited from $20/month. One model that creates and edits, fast: a 1024px image in under 2 seconds on Sogni's GPUs. Here's what you can make with it this autumn 👇🧵

Twin powers, activate! ⚡ Brothers @fishmongr and @krunkosaurus are landing in Singapore for TOKEN2049. Who’s ready to meet them? Oct 7 → luma.com/AI-You-Can-Touch Oct 9 → luma.com/dwfcywj8

What an Nvidia GPU earns on Sogni Supernet in September 2026, before costs and running 24/7: RTX 5080: $174 to $242 RTX 4090: $259 to $357 RTX 5090: $413 to $594 RTX PRO 6000: $813 to $1,102 The low end is the current pool. The high end assumes the pool grows another 50% while your share of the work holds. Built on nine full days of worker activity, with video completions up 92% since Sept 1, most of it MiniMax H3. The worker results behind this forecast come from one carefully managed account. These observed results and forecasts are not evidence of guaranteed outcomes and do not establish what another account or GPU will earn. Actual earnings depend on keeping your machines online, sharing popular models that your hardware supports, keeping your equipment well cooled, and demand on any given day, week or month. Full breakdown 👇

Most AI video breaks in the same place: you generate great shots in one tool, then fight a different one to cut them together. Sogni Creative Agent + @remotion closes that gap. Everything starts with the base, and the base is images and video that actually hold up. Sogni Unlimited gives you 200+ models to generate from, and the agent picks the right one for you based on your prompt. LTX-2.5, MiniMax H3 with native audio, Krea 2, Z-Image-Turbo and the rest, generated in series, whole batches at a time, no credit counting. Seedance 2.5 is there too, pay as you go, for the shots that need it. Remotion turns all of it into a real edit: timing, text, overlays, transitions, transforms, written as code in React. Both live inside your agent. One prompt → generated assets → composed, rendered, finished video. No tab hopping. If you want to try it, one command sets up the Sogni skill: npx setup-sogni-agent-skill Works in Claude Code, Claude Desktop, Codex CLI, OpenClaw, Hermes, or pretty much any agent you already use. We wrote the whole thing up step by step 👇

One TikTok song → character design → full animation, all inside a single agent chat. This is what Sogni Creative Agent was built for - the "I'll just make it myself" era is officially here 😎 👉 npx setup-sogni-agent-skill

Introducing MiniMax H3, now live on Sogni. MiniMax H3 is an open weight video model that generates video and synchronized stereo audio in a single pass. Dialogue, sound effects and music are created together with the image, so every clip comes out finished, not silent. What it delivers: - 5 to 15 second clips at 768p with 32 kHz stereo sound - Text-to-video and image-to-video workflows - Ref2VA multi-reference conditioning with up to 15 files: 9 images, 3 videos and 3 audio clips - Stable dialogue in 11 languages Pricing stays simple: $0.15 per second of finished video, same rate for every mode and aspect ratio. Available today on Sogni Web, the API and the Creative Agent Skill, officially licensed from MiniMax.

You can now subscribe to Sogni unlimited plans using cryptocurrency. Head to swap.sogni.ai, connect your wallet, and subscribe directly on-chain. Payments are supported on Ethereum (USDC/USDT), Base (USDC), and Etherlink (USDC), so you can use the network you're already on. With Sogni Swap, you can pay from any wallet (even a non-Sogni wallet) to any Sogni wallet. Pay-as-you-go plans remain fully supported. You pick the plan and the payment method that fit how you create.

Change the outfit. Adjust the facial expression. Copy a pose from a simple sketch, all while keeping the character consistent. Krea 2 Identity Edit LoRA v1.2 is available on Sogni Unlimited under fair use, making it a great choice for creators who want the freedom to keep experimenting. Here’s the workflow🧵👇

Create on your terms. Whether you're generating around the clock or just when inspiration strikes, the choice is now yours: go Unlimited, or stay Pay-as-you-go. Both paths are here to stay. Sogni Unlimited Subscription Plans are now live. One subscription gives you unlimited fair-use generation across all open-source models on the network, plus 5 to 10% off partner models. Every plan starts with a 3-day free trial. The lineup you'll be putting to work: HappyHorse 1.1, a video model ranking at the very top of global benchmarks. Seedance 2.0 in 4K and the new Mini variant. LTX2.3 with new outpaint, inpaint and transition LoRAs for video editing. Dark Beast Krea 2 and Dark Beast Z-Image for hyper-realistic image generation with unmatched skin texture and detail. One Obsession for expressive illustration and anime. And Ace-Step 1.5 XL for music. Several of these, including the Dark Beast family and HappyHorse 1.1, are unrestricted, with no heavy-handed content filters getting between you and your vision. And that's just the beginning. Sogni's catalog runs deeper than 150 models, spanning every style and medium you can imagine, and it keeps growing every week. Details and pricing 👇🏻

NEW IMAGE MODELS ALERT 🚨 5 powerful new open-weight image models just dropped in Sogni, live NOW in app.sogni.ai Just in time for unlimited use. Check out what these models are and what images you can create with them. A full breakdown with examples 🧵👇

Sogni Unlimited is live 🚀 Fair-use creation across image, video, music, chat, agents & APIs - powered by our distributed GPU network. New models/workflows: Krea 2 Turbo, Seedance 2.0 Mini + 4K, Happy Horse, LTX 2.3, A Step 1.5 XL. Secure your 3-day free trial of unlimited now!👇