Testing out runway’s first frame as a relighting tool.... I relit the frame with Magnific. The Magnific relight isn’t perfect and can change the character a bit but it seems like the runway part stays pretty true to the input.show more

Most AI workflows break the moment you need to... turn one idea into a real project. This started as a single character. It ended as comics, animation, merch, character sheets, and more. The interesting part isn’t the generation. 🧵 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

So this is kinda ridiculous... Claude 3.7 + Magnific... + Runway Restyle. PROCESS: 01. Build 3D Renders in Claude 3.7 02. Program camera movements 03. Screen record render 04. Upload video to Runway Gen-3 05. Extract 1st frame 06. Magnific Struct. Ref. 1st frame 07. Upload in Runway Restyle 08. Generate. I have no idea what I'm doing w 3D. Just kept going down the rabbit hole w. Claude. #runwayml Magnific.ai Runwayshow more

Most AI tools today focus on generation. What’s becoming... more important is everything around the generation: organization, iterations, references, creative direction, workflow. That’s why the Freepik → Magnific transition feels right to me. It already stopped feeling like a single tool a while ago. #Magnificshow more

Kling 2.6 Motion Capture is so good. It's a... huge leap forward. We've been able to do motion capture with AI for a while, but the quality bump finally made this approach useful. Here are the steps: - Get a reference video - record it or get a stock video - Grab the start frame of that video - Edit it using Nano Banana Pro. Ask to replace character and background. - Select the Kling 2.6 Motion Capture model in the video generator on Freepik (now Magnific) - Upload reference video + set the edited start frame - Video prompt can be simple e.g. "Gandalf dancing"show more

I wanted to try i2v on Kling by specifying... the first and last frames, but it seems the free version has a monthly usage limit, so I couldn't do it this month. So, I had no choice but to specify only the first frame—and here’s the result, lol.show more

New emergent capability with Grok Imagine image references: You... can use them as first and last frame with a bit of prompting. Prompt in the post.show more

❤️ Runway Aleph 🔥🔈 Testing combining rapid camera movements... with preserving core of base video action. example: 'leaving the first frame unchanged, move the camera extremely rapidly to an aerial view above this explosion while keeping the focus on the explosion, then zoom the camera out to reveal the entire complex' Wonder if I can specify the final frame via image reference. Last video is original.show more

Voice, music, and SFX from a single prompt Seed... Audio 1.0 is now on Magnific → Scene control: environment, voice, emotion, music, SFX → Multi-character dialogue → Texto-to-audio, up to 3 reference audios or image Available on the Magnific Voice Generator, MCP and Spacesshow more

GPT Image 2 + Seedance 2.0 - Prompt Share... Created on @MartiniArt_ Created the character in Midjourney, then built the storyboard around that character. This time I used a more detailed video prompt, but I wasn't describing the sequence shot-by-shot. The storyboard acted more as a visual guide for the action flow, camera language and overall narrative than as a strict frame-by-frame blueprint. Looking at the result, the model seems to preserve the key beats, escalation and composition of the storyboard while freely interpreting the transitions between them.show more

#whaanimespoilers also i definitely think i found the brim’s... initial attack here a bit more frightening in the manga, what with it suddenly smothering the entire frame… but i actually still really like the way they animated it, all shifting and steadily engulfingshow more

And I got a bit confused with the cover... but I always uploaded pink to the site and I can't change it.show more

Here are some really tactical ways to optimize the... First and last frame capability: — Make sure your prompt includes precise camera motion descriptions for smooth and creative transitions between the first and last frames. — Or, you can simply include the word “transform” in your prompt for a smooth transition — Starting with a closeup in your first frame and then zooming out to a wide-shot in the final frame is an effective way to create a dramatic reveal.show more

Justin T. UVU Palmer Luckey I'm glad you brought... that to our attention. I think this one is a bird and that's good to compare. This one is moving up and down in a more organic way as it flies left to right and the shape seems to change frame over frame. I also see motion blur that looks like wing flapping.show more

Do you use Runway Gen-2 to make AI videos?... This is for you! I built a simple tool to help "extend" Runway videos beyond the 4 second clip limit. Just choose a video, and the tool will give you the final frame -- so that you can drop this back into Runway, and generate another AI video based on it. Let me know if this is useful to you! Link is at bottom of the video and it's live to try right now.show more

Parker Jennings (‘25 CA) opening up 89-91 with late... life. Going to a tight tilting slider at 78-81 with late bite and can land it. Throws the change to lefties at 85. Lean and lengthy frame and can still fill out. Projectable with more in the tank. #Elite #OSU commit. Perfect Game California Alpha Baseballshow 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

Testing SCAIL-2, an open source model for motion transfer.... I wanted to see how it can handle driving videos with fast, dynamic movement. The part that really impressed me was how the model retained details from the input character's outfit (especially the straps on the shorts). I attached the input character below for you to compare against. The model also has a replacement mode that swaps the character into the driving video's scene, but here I used animation mode, which keeps the reference image's scene instead.show more

This Relight tool is insane 😱 You can completely... change the lighting of any image in seconds. If you work with images, you need to try this. Comment “Relight” and I’ll send it to you ⬇️show more

I meant it ... for real... I generated those... 3 videos to show you what we can do now with a simple prompt they're not perfect but good enough with a bit of editing the seedance 2 credits allowance seems quite generous the more AI makes huge leaps like this... the more it became unforgivable to not make $10K a month ps: I'm not sponsored by higgsfield I'm shared a cool tool - that's itshow more