Lovis Odin
@OdinLovis • 8,572 subscribers
AI / Technical Artist / ComfyUI expert • Training models • Creating crazy workflow • Creative Engineer at https://t.co/SpUceQW1mb • SF based • Old Gobelins Paris
Shorts
Videos
, webgl experience fully made using fal the pipeline: GPT-Image-2 (or FLUX.2 Klein 9B for the live "create your own") 🦴 meshy v6 image-to-3d takes that → rigged GLB with a baked animation 🐾 GPT-Image-2/edit on the same character → companion creature image, color-locked to the character's palette → meshy v6 again (no rig) → static creature GLB 🪨 PATINA (fal-ai/patina/material/extract) takes the character image and outputs basecolor + normal + roughness + metalness for a per-character floor that matches their environment 🎬 Seedance 2.0 fast → 8s looping background video per character 📦 everything runs through gltf-transform (resize 1024 → webp q80 → draco) for ~95% size reduction → 400-800 KB GLBs 🖥️ the front-end is a single static index.html: Three.js scene, alpha-mapped marble disc with PlaneGeometry tessellation for real displacementMap depth, mirrored reflection plane, breathing animations on companions, palette-swap via CSS custom properties on character click 🧩 the whole recipe is published as a Claude Code skill fal-regenerate-3d so you can rebuild this yourself → ⚠ metrics shown are decorative
Lovis Odin94,278 görüntüleme • 1 ay önce
To celebrate nano-banana-2 launching on fal , I built FalSprite, sprite sheet generator that turns a text prompt into game-ready animations. One key powers the whole pipeline: → nano-banana-2 for image generation → BRIA for background removal → OpenRouter LLM for prompt rewriting ~$0.20 per generation. Try it live or fork it: 🔗 🔗 Thanks Blendi for the help on this 🙏
Lovis Odin65,208 görüntüleme • 3 ay önce
I built a bot on an ESP32 that can create full projects by itself. Ask it to generate images, videos, 3D, build a website and publish it, it does everything autonomously. Powered by Claude Opus 4.6 for code, visual content generated with fal, bot powered via OpenClaw🦞 The skills to generate project with fal are here All running on a tiny M5Stack Core2.
Lovis Odin50,291 görüntüleme • 3 ay önce
Google Veo3 creates beautiful base videos, but what if that’s not enough? I built a ComfyUI workflow that takes it further: 🏗 New structure with Flux (LoRA arch) 📦 Turned into 3D with Hunyuan3d 2 🔁 Integrated + relight via Flux, Controlnet, Denoise and Redux 🎞️ Finalized the video using Wan2.1 + CausVid + VACE The result? Custom, controllable, cinematic videos far beyond the original VEO3. ⚠️ There are still a few scale and quality issues I'm currently working on, but the core process is solid. 📹 I’ll drop a full video tutorial next week. 📁 In the meantime, you can download the workflows, links in the comments (I am using a H100 for it, but probably a A100 is enough).
Lovis Odin88,871 görüntüleme • 1 yıl önce
4 billions years - part 1 , made in 2hours with Seedance 2.0 on fal using api . Semi-automatic process vibe-coded. Monday I will share the full video and a tutorial on how to make this yourself ! Look at the end if you want to see Dinosaur ! I will show also how to do calibration of lighting etc..
Lovis Odin19,839 görüntüleme • 2 ay önce
This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)
Lovis Odin56,518 görüntüleme • 8 ay önce
Everybody speak about consistent character for video generation as Minimax, Kling etc... But nothing looking super stable. And so I trained for the first time a LoRA model on Hunyuan video model (open source) on a real person. It take approximatly 15h of training on a A100 GPU with 50 videos. the result is pretty good !! With more training it will allow to have even better result. The result was generated inside ComfyUI. All this video have been generated in AI. Check at , we are doing cool stuff :)
Lovis Odin93,518 görüntüleme • 1 yıl önce
📦 : I di this ComfyUI workflow for Sora 2 upscaling 🚀 ( or any videos ) Progressive magnification + WAN model = crisp 720p output from low-res videos using Llm and Wan Built on cseti007's workflow as base ( Open source ⭐ It does not work super good at keeping always consistent face for now More detail about it soon :)
Lovis Odin33,121 görüntüleme • 7 ay önce
Starting from a sketch of 1900 to transform it using ComfyUI ( AI ) and integrate it automaticly. I am presenting this workflow Friday 19th at 3pm PST on the twitch of Civitai . Hope you will be their ! I am using ComfyUI to do sketch2img, imgto3D, 3D2img, integration using differential diffusion, ic-light etc.. I will show you how to create a 3D model and how to integrate it directly inside ComfyUI ;) #architecture #ai #interior #comfyui #3D
Lovis Odin77,236 görüntüleme • 1 yıl önce
Old Art to full 3D using Cinema 4D . Created a free and open-source plugin to bring Hunyuan 3D directly into Cinema 4D. This workflow combines multiple tools that are available today into a single, cohesive pipeline. I wanted to show that AI is never an end product by itself, it’s not the finality. Used properly, AI becomes an extremely powerful tool that lets you build exactly what you want. I hope you like it. The final step will be to bake all textures so I can share the project as a WebGL experience, a small interactive website to explore it directly in the browser. Made with heart, and with fal ❤️
Lovis Odin21,832 görüntüleme • 4 ay önce
I Built an open source virtual try-on professional LoRA at fal Lora for Flux Klein 9b Edit, give it a photo of someone + 2 clothing items and it dresses them up Works with men and women, all kinds of outfits Weights are open on HuggingFace, and there's a playground you can try right now
Lovis Odin15,294 görüntüleme • 3 ay önce
1989 hardware + 2026 AI I open-sourced a tool that turns any photo into a playable Game Boy ROM using AI. It only take one minute in total ! Made with fal to generate pixel art, then optimizes it for Game Boy's brutal constraints (4 colors, 256 tiles, 8KB RAM) Result: your photo becomes a playable .gb or gbc ROM with: - Animated character (idle/run/jump/attack) - Scrolling background - Music & sound effects Open source (Windows) Much more to come :)
Lovis Odin17,575 görüntüleme • 5 ay önce
Generate image, 3D, and video from a single sketch in one click in ComfyUI with AI! I’m excited to share a cutting-edge workflow I’ve developed that combines inside ComfyUI: Runway with fal. ai api (yes there is a node for it :) ), Stable AI’s stable fast 3D , powerful Flux, ControlNet, IPAdapter, Gemini LLm in ComfyUI. This innovation allows you to generate high-quality visuals and 3D models, reposition objects, and create videos—completely automated from a simple sketch input. Would you link a tutorial for it ? #AI #ComfyUI #3DModeling #Automation #CreativeTech
Lovis Odin36,767 görüntüleme • 1 yıl önce
After long months , I am so happy to share probably one of the biggest and most early project using mostly ComfyUI (in march) and other AI tool to generate a full animation movie. this project was a Real team project made with DOGSTUDIO/DEPT® for Coca-Cola . Second part IS making off ! Hope you will like it !
Lovis Odin33,575 görüntüleme • 1 yıl önce
🚀 Just released a LoRA for Wan 2.1 that adds realistic drone-style push-in motion. Model: Wan 2.1 I2V - 14B 720p Trained on 100 clips — and refined over 40+ versions. Trigger: Push-in_camera 🎥 + ComfyUI workflow included for easy use Perfect if you want your videos to actually *move*. 👉 #AI #LoRA #wan21 #generativevideo ComfyUI Made in collaboration with Kartel.ai
Lovis Odin18,366 görüntüleme • 10 ay önce
Consistent character with Hunyuan and Skyreel! 🎥✨ In collaboration with Kartel.ai .ai, we worked on a pipeline using ComfyUI with the Hunyuan & Skyreel models—both designed for video. We first captured him volumetrically, then trained a LoRA model directly on video data, allowing us to generate sequences where a person remains consistent across shots. The goal is to maintain identity and style over time, pushing the limits of AI-generated video. Excited to explore this further! 🔥 with J. Salvatore in main actor , thank you ! #AI #GenAI #ComfyUI #LoRA #VideoGeneration #Hunyuan #Skyreel
Lovis Odin13,348 görüntüleme • 1 yıl önce
Daha fazla içerik yok.