Reference images in. Final cinematic sequence out. What I... like here is how closely the final video follows the original visual direction instead of drifting away from it halfway through. Magnific (formerly Freepik) #Magnificshow more

Starting from only a few reference images… Magnific Spaces... turned them into a complete cinematic video sequence. The final result keeps the same mood, style, and visual identity surprisingly well across the entire clip. Magnific (formerly Freepik) #Magnificshow more

These reference images were used as the starting point.... This is the final cinematic video generated with Magnific Spaces. Feels much closer to a real visual development workflow than isolated AI generations. Freepik becoming Magnific honestly fits the direction of the platform now. Magnific (formerly Freepik) #Magnificshow more

Camera control is no longer in the prompt Meet... 3D Motion Control → Set the camera path in 3D → Your scene becomes the video reference the model follows → Same move, every take, exactly where you set it Available now in Magnificshow more

Hedra Agent 2 turns a simple concept into a... full creative production workflow. Hedra I gave it a challenge: “What could New York look like in 2050?” It researched future urban trends, developed the creative direction and script, then built the visuals and final cinematic sequence. What stood out was how the entire process—from research → concept → planning → production → final videohappened in one Space. Workflow 👇show more

And here I tried Haiper AI again, and is... really good, I really like it, so as always I used Midjourney V6 images, and upscaled them with Magnific...hope you like it, you can find the images plus the prompt below 👇😉show more

Watch this cinematic AI video come to life. I... created this shot with Wan 3.0 on Magnific and the result looks straight out of a movie. The movement, atmosphere and detail are seriously impressive. Wan 3.0 is 40% OFF until September 30.🎉 Try it here:show more

I know sora 2 is the talk of the... day but I was making this just as fun with Kling AI. (Would love to see someone trying this idea with sora 2) 👉 Freepik (now Magnific) nano banana and seedance 4 images. 👉 CapCut editing and sound. Like, share, bookmark, Image prompt in reply.show more

MiniMax H3 is now 50% OFF on Magnific for... 2K video, only until September 1. 🔥 I’ve been trying MiniMax H3 on Magnific, and it feels like a big upgrade for AI video creation. It’s not just about turning text into videos. You can use text, images, videos, and audio together in one prompt, giving you more control over the final video. Here’s what makes it stand out: - Multimodal: Use text, images, video, and audio in one prompt. - Multiple references: Add up to 9 images, 3 videos, and 3 audio files. - 2K video: Create videos up to 15 seconds long. - Built-in sound: Generate voice, music, and sound effects with the video. - Easy editing: Remove objects or transfer motion easily. - More control: Control the camera, characters, and voice. You can use it to turn posters into videos, moodboards into short films, and product images into ads. It also helps bring your ideas to life with realistic movement, lighting, reflections, and sound. The workflow is simple: give it your references → generate → edit → refine. Try MiniMax H3 on Magnific:show more

Okay, this is the kind of AI video that... makes you watch the clip twice. Wan 3.0 on Magnific surprised me with how well it handles dialogue, camera movement, and character consistency in the same generation.show more

By combining Pika Pikaframes and Freepik (now Magnific), I... now have the magical ability to jump through space and time and in this example, music becomes a transformative element teleporting this woman to a new location. This is how it's done. 1/6 🧵 The videos below are fully narrated so make sure to turn on the audio 🔊 Yes, you'll need a subscription on both Freepik and Pikaframes if you want to create something like this, I would rather be honest and tell you from the start 👍show more

Magnific 'Structure Reference' + RunwayML "Restyle video" to colorize... old movies ... I think one might run this in a way you use this to help to determine the color layer and then apply the colors on top of the original black and white image... ... would work best if you would do a separate init frame for each cut...show more

Today I got interested in how horse carriages turn... the front axle independently from the rest of the carriage. So I combed through a bunch of images and videos to find out how the undercarriage is built.show more

Most AI video tools generate clips. The interesting ones... help you build a complete creative workflow. MiniMax H3 stood out because it can use text, images, audio, and video together with Omni Reference. That makes it easier to keep the style, branding, and creative direction consistent from the first prompt to the final video. What caught my attention: • Text + image + audio + video inputs • Native 2K video generation • Better control over edits and refinements • Built for ads, e-commerce, gaming, and branded content AI video is moving beyond single prompts. It is becoming a creative workspace.MiniMax Design (H3) Try here 👇 #hailuoai #hailuo #MiniMaxH3 #H3 #AIVideo #GenerativeAIshow more

Every character in this universe starts the same way.... A line. A feeling. A direction. The Alien male, from first sketch to final. This is what building a race looks like.show more

MiniMax H3 is a serious upgrade for AI video... creation. Instead of relying on just text prompts, you can combine images, videos, and audio references to control the character, motion, camera, and sound. What stands out: → Up to 9 image + 3 video + 3 audio references → Native synced voice, music & sound effects → 2K video generation up to 15 seconds → Instruction-based video editing → Motion transfer → Better character, camera & voice control The interesting part is that you can build a full scene from references instead of endlessly regenerating until the result feels right. 🔗 Now is a great time to try MiniMax H3 on Magnific, especially with the current 2K offer.show more

#sally I loved sooo much the concept that Diz... made, so I tried to emulate in this 3D model as closely as possible. It was difficult but here is the final result💜🎃show more

With the release of Aemondir skin on Valorant today,... Here is my anim process for the right click melee. As usual, you'll see my video reference, maya anim, and final in-game.show more

Seedance 2.0 editing mode is extremely powerful. You just... need to add the reference and make a simple request — it understands and follows the exact same movements from the original video, adding the characters you asked for in sakuga quality, like Nami vs Maki. It’s only a matter of time before AI does this perfectly. The internet as we know it is about to change.show more

So much of the complexity for multimodal/robotics data is... just getting the right format that's both flexible and performant. I dig into it here in the context of 3d reconstruction. I'm hoping to build an opensource arkit like pipeline and explain the first bit for the data pipeline here! Heres a video of what the final data looks like in a registered catalogshow more