I wanted to see how far H3 Max could go with just a video prompt. So I tried to recreate the wormhole sequence from Interstellar — spacecraft movement, gravitational lensing, camera movement, spacetime distortion, and the transition through the wormhole. No manual VFX. No compositing. Then I ran the same concept through H3 Max Turbo. What surprised me most wasn’t just the visual quality. It’s how much of the description the model can actually translate into motion. Video models are getting better incredibly fast. Which one do you think did a better job? 👇

First of all, I want to say a huge thank you to everyone in this community for joining us and putting in the effort to get better at AI. We genuinely appreciate every single one of you. We couldn’t have reached this milestone without you. The people inside this community are some of our realest supporters, so we wanted to give something back. ❤️ For the next 𝟕𝟐 𝐡𝐨𝐮𝐫𝐬, we’re giving away our Blender → Seedance add-on completely FREE. Normally, this is a paid skill, but as a thank-you for helping us reach 1,000 members, you can now claim it for free on our website. Go grab it, start creating, and experiment with it. Here's the link: https://drive.google.com/file/d/1dUGgS7avLvA8MZEURI2G_sFRcZHXgCYc/view?usp=sharing And as a little extra, the skill also includes a 𝟏𝟓% 𝐝𝐢𝐬𝐜𝐨𝐮𝐧𝐭 for OpenArt if you want to use it — 𝐓𝐎𝐓𝐀𝐋𝐋𝐘 𝐔𝐏 𝐓𝐎 𝐘𝐎𝐔! And once you’ve made something, share your visuals here in the community so everyone can see what you created. I’d also love to hear your feedback and see how the skill is working for you. Again, thank you for being part of this community and helping us reach 1,000 members. 🙏 You have 72 hours to claim it for FREE. 𝐏.𝐒. 👀 𝐖𝐞’𝐯𝐞 𝐠𝐨𝐭 𝐬𝐨𝐦𝐞𝐭𝐡𝐢𝐧𝐠 𝐁𝐈𝐆 𝐜𝐨𝐦𝐢𝐧𝐠. Something that will completely change the way you create content using our GPT models. We’ve been working on this behind the scenes for a while, and I can’t wait to show you what’s coming. Stay tuned. 🚀

The crazy part is how much you can do with this style once you get the right prompt structure. Different dishes, camera angles, little crochet details… it’s surprisingly fun to experiment with. I’ll drop the tutorial very soon 👀 Would you guys want to try it?

Ran the same prompt through both video models again, this time an otter on a raft that falls in the water and ends up riding a turtle. Both 15 seconds at 720p. They followed the same shots, but the look is completely different. The prompt asked for cinematic 3D animation, and Wan 3.0 stuck to that: higher contrast, bigger eyes, bright blue water with bubbles. Seedance 2.5 drifted a bit more toward photographic realism instead, with grey-green mist, pine forest and murky water. In the end it all comes down to taste. Wan 3.0 gives you the more animated version, and at $1.50 against $3.15 for the same 15 seconds that's worth taking into account. But I really liked the Seedance 2.5 output too. Which look fits your content better? 👇

Great to have you here! @Ashley Delph @Orlando Ordonez 👋 Feel free to introduce yourself below and tell us: What are you currently using AI to create?