New open source LoRA Multi-Angles I created with fal... for Flux.2 🔥 Flux2.-Lora-Multi-Angles: give a camera angle in degrees → get your image from that view. To build this, I created a system that captures 72 positions from Gaussian Splatting to generate the training dataset fully automatically in a webgl viewer. ▶️ Test: 📥 Weights: Should I open source my WebGL viewer so you can train your own from gaussian splatting ?show more

🧮Turn single image into a custom LoRA model in... one click ! Should work for character and product ! This ComfyUI workflow: → Uses Gemini AI to generate 20 diverse prompts from your image → Creates 20 consistent variations with FLUX.1 Kontext → Automatically builds the dataset + trains the LoRA One image in → Trained LoRA out 🎯 #ComfyUI #LoRA #AIArt #FLUX #AutomatedAI ComfyUI BlackForestLabsAI - Unofficial 🔗 Check it out: This workflow was made for the hackathon organized by ComfyUI in SF yesterdayshow more

Yeaah with Kartel.ai and Jesse Wellens ! So training... Lora for character on Flux and also for Wan 2.1 14B ( using dataset video ) make a Huge difference. So here you are seeing a volumetric capture of Jesse Wellens that we did in at the spatial studio of Kartel.ai We use a a World Labs gaussian splatting to create a simple environment that we put with the volumetric capture in our own webgl viewer ( out soon for everyone ). After that, We use after this output in a ComfyUI workflow with Wan Fun control ( a bit similar Vace but its working for Wan 14B) with the double loras , the first to generate the first frame with flux, and the second one to guide the generation of Wan 2.1 Control. So we keep very good consistency of character and position, and creating amazing worlds :) ! Hope you will find it cool !show more

I am really super happy to show you my... research that transform 3D volumetric capture of man capture with Kartel.ai and with env gaussian splatting generated with World Labs in a three.js player . And all that is "upscale" using Hunyuan vid2vid model with a Lora train on videos on the main actor. Hope the future of movie is here :) . Still need some work, but you can get the ideashow more

This is the first Gaussian splat I ever created... - a self-portrait from Nov 2023 scanned with Luma. The PlayCanvas Engine has come so far in the last 2+ years. SuperSplat can now stream splats of unlimited size with precise collision and crazy performance. Free and open source. 🚀show more

I built a plugin to generate 3D assets directly... from Codex, using the latest update that introduces image generation. It generates an image, calls the Tripo3D API, then starts an MCP server and a local viewer directly inside Codex. It uses the paid Tripo3D API (12 free generations, 600 credits included). Everything is open source on my GitHub. Link below. Feel free to contribute. Room for improvement: skeleton/animation support and multi-provider 3D support.show more

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from... In-the-Wild Drone Imagery Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.show more

Stop relying on generic AI output Train a model... on your world, your character, your style, and reuse it forever That is the idea behind LTX Trainer, an open-source training framework that lets you train reusable IC-LoRAs for specific video transformations like colorization, deblur, decompression, reference sheet control, and a lot more Each LoRA gives the model a specific behavior it can repeat across clips, so your videos become more consistent, more controlled, and more connected to your own creative direction Check these amazing examples 👇🏻show more

Today I am experimenting with visionOS 27’s native Gaussian... Splat Rendering It’s limited to 200,000 splats, BUT due to this, you can render them in shared space Zmienny helped train a rough test scan of my Rem figurine that I could place right next to the real one. Awesomeshow more

FSD save lives. (video update) As many people still... don't get the right perspective from the original accident dashcam, I'm uploading a new one with all combined angles (just 4, no space for all 6) to give a more realistic view. I can't adjust for the different perspective angles, but color and speed were synchronized as much as I could with the other dashcam angles so people can have more a more realistic experience with what happened.show more

I can also convert source files from PS3, the... highest quality base version of the Sonic 06 cutscenes. Their audio is stored in a proprietary format as well which is separated by layers meaning that I can get rid of music from cutscenes. Add your own, I beg of you.show more

for some brands from the L’Oréal group, I created... this prompt to easily generate an isometric office diorama that can be adapted to any brand and material it works with a simple Nano Banana 2 prompt and is easy to animate with Kling 3.0 this is how I imagine my future officeshow more

Because many of you asked, I created a ref... link last month for Drift. I promised to abide by my word of "I will never profit from my audience" Today I gave away all earnings from the ref link to one of to a randomly selected wallet who is one of the people that used the link. I will continue to give away all earnings monthly. Congrats to: 3c9Nrw4ffVnyb5ZEp8dWfdxWNrAhToUMaHgmu7s3Jvq5 May the unexpected USDC in your wallet make your day a bit brighter.show more

🔥 VIDU Multi-Entity Consistency Give Vidu 2/3 images and... it’ll turn them into a video—it’s pure magic! ✨ Your own characters interacting with objects and in the exact environment you want! Ads, movies… endless possibilities, and this is just the beginning! Thanks @Viduforhuman The future is a carrot! 🥕 Plus, how about grabbing any frame from a Vidu-generated video "from scratch" and throwing it into another AI video or image tool to push your project even further? For now, check out the comment below: I scaled up a frame with Magnific.ai and fed it into Runway to create a dynamic shot using full camera control. But fingers crossed I can soon use #ReCapture by Bisho & team to generate new shots from the same video!show more

A preview of what's next, visualized with Rerun and... PlayCanvas supersplat ✨ (Also, feel free to send me a DM 📩; I’ll be in San Francisco from July 21–29, and I'm looking to meet like-minded folks!) I'm convinced that Gaussian Splats will be an integral part of any data engine as an underlying representation. So I've started putting together a repo that: 1. Given a single image, perform image outpainting 🖼️🖌️ 2. Estimate a monocular depth map on the outpainted image 📏 3. Train a Gaussian Splat initialized from the monocular depth 🎓✨ 4. Warp to new views, perform inpainting on the missing masks -> Train new splat 🔄🎨 This is going to be integrated into exo-egoforge, but I wanted to start with the simple single-image version before moving to a multi-video implementation There's some weirdness in the final rerun visualization, but the trained splat looks great 🎉! This is all based on the very cool VistaDream paper ( .github.io/) More on this next week!show more

The quoted video was created using clips from three... different videos generated with nearly the same prompt. After that, I only did a bit of color grading. You can find the prompts used for this video in the replies. GPT Image 2 + Seedance 2.0show more

Midjourney sref + Sora 2 Pro is the sauce.... With one Midjourney style image, you can give a specific style for your entire project. I created two different 12-second clips and edited them together. Some details aren’t fully consistent, like the iPod or AirPods because the clips were made separately from a single image (Character in a specific style). It could be fixed in post-production, but that would take more time, and this was more of an experimental test. It would be great to add the actual product image with the current one to maintain product consistency. I feel like if there were a way to add 2–4 images into this workflow, it could open up a lot more possibilities and consistency. With an API, it could be possible. Or let’s see what Veo 3.1 has to offer.show more

We have just reached 200 followers And as a... celebration, I will give FOR FREE the 3 AE PROJECTS that I have shown in my profile So you can learn from them. All you have to do is: 1. Follow 2. Reply “G". See you in your DM's!!show more

Huawei's new 3D lock screen wallpaper is actually pretty... interesting. Unlike iPhone's Spatial Photo, which creates a fixed stereoscopic depth effect from a photo, this lets you scan an object 360°, generate a full 3D Gaussian Splatting asset, and use that as your lock screen. Tilt the phone and you're moving through a reconstructed 3D scene, not a fixed stereo image. The part worth paying attention to: 3D capture moving out of creative pipelines and into everyday phone personalization. That's a different kind of adoption curve.show more