Natalie (@NatalieCrypto6) header
Natalie (@NatalieCrypto6) profile picture

🔗 @Sogni_Protocol team ♥️ 🔗 AI projects obsessed 🔗 Content Creator Discord: nataalkaz (Natalie) 100% web3 & crypto

Joined November 2022
Photo by Natalie (@NatalieCrypto6)Photo by Natalie (@NatalieCrypto6)Photo by Natalie (@NatalieCrypto6)Photo by Natalie (@NatalieCrypto6)Photo by Natalie (@NatalieCrypto6)Photo by Natalie (@NatalieCrypto6)Photo by Natalie (@NatalieCrypto6)Photo by Natalie (@NatalieCrypto6)Photo by Natalie (@NatalieCrypto6)Photo by Natalie (@NatalieCrypto6)
GM web3! 🚨 Make sure to play it with sound! 🚨 You’ve got a problem - you don’t know what’s real anymore. Is this still normal? This level of AI video quality? Amazing and terrifying at the same time. You can create… ...your own avatar, that speaks like you... reacts like you... records content for you... You sleep - your clone works 😱
21
12
1
100
10,434
You often ask us what Sogni Creative Agent can do, but at this point, the better question might be: what can't it do? 😏 Well, here's a little taste of what's possible with just one AI agent: - Films that tell a story - Campaigns born from one brief - UGC that feels real - One sketch, endless styles - Old photographs brought back to life - Worlds you can step inside And this is just a glimpse of what you can build. Create freely on Unlimited, and reach for premium models pay-as-you-go whenever a project calls for more. Bring it into Claude Code, Codex, Hermes or any agent as a skill, or connect it as an MCP server. Got an idea? Let's bring it to life 👇
25
8
1
55
2,013
do you guys already have your own creative team inside your AI agent?
Create entire marketing campaigns with one prompt. This LIPHAZE campaign started as one sentence typed into Claude Code. Every photo and video in this film came from it. Sogni Creative Agent is a creative team that lives inside your AI agent: Claude Code, Codex, Hermes or any other, in the terminal or on desktop. You write the brief, it handles the rest: → Locks your product, so the label, shape and color stay true in every shot, or designs a completely new one from scratch → Casts the shoot: locations, faces, light and mood that fit your brand → Picks the right model for every image and video, from the ones included in Sogni Unlimited or pay-as-you-go models like GPT Image 2, Seedance 2.5 and Wan 3 → Turn your best shots into ads for Reels, TikTok, and Shorts, or any other aspect ratio → Delivers it all to one folder and takes notes like a director: "warmer light", "new location", "more motion" Production used to be the expensive part of a campaign. Now it's the idea. Set it up👇
4
14
74
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 👇
20
10
1
67
2,389
What do you think? Creepy, too creepy, or just perfect for Halloween? Created in Claude Code for artistic purposes using Sogni Creative Agent with just one prompt! Krea 2 for images MiniMax H3 for videos
2
3
11
203
Seedance 2.5 is available on Sogni with pay-as-you-go pricing and up to 10% off for Unlimited subscribers 👇
Seedance 2.5 on Sogni now turns photos of real people into video. Make a full UGC ad like this one: 1080p, native voices, any location you want. No celebrities, public figures or anyone without consent, you're responsible for what you create. Here's how 👇🧵
2
3
13
164
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 👇🧵
12
17
1
58
2,766
Editing photos with AI is still hard. Change the hair and you get a new person. Ask for a pose and the face drifts. So we ran an honest test: one selfie, the same prompts, 8 edits and 25 yoga poses, across four editors on Sogni: • Sogni Krea 2 Identity Edit v0.3 (Unlimited) • Krea 2 Identity Edit v1.2 (Unlimited) • Dark Beast Krea 2 Identity Edit (Unlimited) • GPT Image 2.5 (pay as you go) No retouching, just what each model gave us. TL;DR: some models nail everyday edits like hair, outfits and new locations. Others are better with poses. The full guide with every prompt drops on our blog this week. Until then, here are the results 🧵👇
14
7
1
41
5,070
"Sogni" means dreams, and we're bringing them to TOKEN2049 in Singapore: a crew of dreamers who live and breathe creative AI and can't wait to meet you. Catch us at AI You Can Touch with OpenBuilder and TZ APAC. You'll try live demos on two connected DGX Sparks, play with an open multimodal model straight from your phone, and hear a panel on owning your own AI instead of renting it from the cloud. Bring your wildest idea and come say hi 💚
18
6
44
2,037
the Sogni team when someone says "just one more generation" 🕺 Wan 3.0 and Wan 3.0 Enhanced inside Sogni are made for recreating the trends you can't stop watching. Pick a viral clip as your video reference, add a photo of yourself and tell it who you want to swap with. You can swap just the face, or put yourself in the scene in any outfit you choose. It keeps every move, the timing and the vibe, just with you in it - pay as you go on Sogni. Check it out, link below 👇
8
2
38
2,347
Make a full commercial starring yourself, from one selfie. All it takes is a photo of your face, your product and a description of the ad you have in your head. The agent turns that into prompts and keeps your face and outfit consistent across every shot. This one was rendered with Wan 3.0, which right now gives some of the best character consistency you can get in videos of yourself. Here is the exact workflow, step by step, with every model used along the way. Save it for your next campaign 👇🧵
15
23
1
66
2,380
This is a real game changer 😍
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 👇
2
4
26
290
🔊 Sound on. So… where’s the line between real and AI now? 👀 Does this still look fake, or are we finally at the point where you have to do a double take? I honestly think we’re right on that edge where the line between real and AI is starting to disappear. Now available in @Sogni_Protocol: Seedance 2.0 and Seedance Mini & 4K.
🤖 Made with AI
4
6
29
325
Listen 😂 People are having fun creating cool stuff for the project in real life and people still keep saying it’s AI-generated. I love AI, but why do we even have to prove that something was made in real life? 🙈 Proof below 👇🏻
Onboarded two girls to @avax on my holiday in Turkiye 🇹🇷 Even 100m in the air, all they could talk about was $hotemin summer 🔺️☀️ This is not AI in case anyone is wondering
7
2
23
759
Natalie retweeted
Onboarded two girls to @avax on my holiday in Turkiye 🇹🇷 Even 100m in the air, all they could talk about was $hotemin summer 🔺️☀️ This is not AI in case anyone is wondering – at Manavgat, Türkiye
20
9
1
67
2,933
Honestly, Sogni Skill inside Claude is kind of wild. 🤯 You type a prompt in the terminal and get an entire workflow in one place. On top of that, the brain behind it is Opus 4.8. Do you realize what you can generate with this setup? And how fast? And that’s not even mentioning that Seedance 2.0 and GPT Image 2 are in there too. This is just a simple example: ✅ 10 generated images ✅ 10 generated videos ✅ automatically stitched into one final video All in about 3-4 minutes. That’s a real game changer. I’ve already had a chance to test it and even someone with amateur-level vibe coding skills like me can build pretty much anything with it 🔥
🤖 Made with AI
2
2
20
485
It’s incredible what you can generate nowadays 🤯
Your posts inspired us so much that we decided to create our own cinematic LEGO-style commercial inspired by the newly unveiled Ferrari Luce 🏎️ Built entirely in Sogni Chat, we followed one of the hottest creative workflows right now: storyboarding with GPT Image 2 + video generation with Seedance 2.0! We wanted to reimagine this futuristic Ferrari in a LEGO universe - the kind of dream every kid had (and secretly still has 🤫). And honestly… can you already feel the vibes? 🔥 Storyboard below 👇
2
3
22
208
Just had this crazy idea for a new choreography for Shakira! I turned her into an animated version, built the storyboard in GPT Image 2 and used Seedance 2.0 to turn it into a video - all in Sogni Chat by @Sogni_Protocol What do you think? 💃
4
2
16
378
From idea to final cut without switching tabs. Seedance 2.0 and GPT Image 2, available on Sogni Chat, open a completely new chapter in generative AI: → Marketing campaigns ready in minutes → Visual storytelling at studio production level → Virtual influencers building your brand → Dance choreographies generated by AI …and so much more Everything in one ecosystem - no tool fragmentation, no compromises chat.sogni.ai.
19
10
1
56
3,098