Lovis Odin's banner

Lovis Odin

@OdinLovis • 10,480 subscribers

AI / Technical Artist / ComfyUI expert • Training models • Creating crazy workflow • Creative Engineer at https://t.co/SpUceQW1mb • SF based • Old Gobelins Paris

Shorts

I see many people doing this kind of effect for their video, but I was like, mm why a single video, why not to do that to showcase the power of h3 max director on fal and how it can take different path and visualize in live ! Inspired by Brandon Eversole Much more to come, this was just made in a few minute

I see many people doing this kind of effect for their video, but I was like, mm why a single video, why not to do that to showcase the power of h3 max director on fal and how it can take different path and visualize in live ! Inspired by Brandon Eversole Much more to come, this was just made in a few minute

37,893 просмотров

MCP Claude that have full control on ChatGPT 4o to generate full storyboard in Ghibli style ! All automatic I am doing nothing at all, we live a pretty crazy time Anthropic OpenAI

MCP Claude that have full control on ChatGPT 4o to generate full storyboard in Ghibli style ! All automatic I am doing nothing at all, we live a pretty crazy time Anthropic OpenAI

404,694 просмотров

I made the workflow for comfyui to use Ltx 2.3 render to real Ic-lora ! If you want to go fast you can just use our endpoint : workflow available here :

I made the workflow for comfyui to use Ltx 2.3 render to real Ic-lora ! If you want to go fast you can just use our endpoint : workflow available here :

30,588 просмотров

👉 I created « Next Scene » for Qwen Image Edit 2509 and you can make next scenes keeping character, lighting, environment . And it’s totally open-source ( no restrictions !! ) Just use the prompt « Next scene: » and explain what you want. I trained it on hundreds of paired shots to preserve characters, lighting, and mood between scenes. ( Soon I will explain what tools I created that can manage classification and caption of data when you have more than 10 000 of items, using workers and a total new way to classify data ) . Built for storytellers working with ComfyUI or other diffusers pipe ;) ! ComfyUI

👉 I created « Next Scene » for Qwen Image Edit 2509 and you can make next scenes keeping character, lighting, environment . And it’s totally open-source ( no restrictions !! ) Just use the prompt « Next scene: » and explain what you want. I trained it on hundreds of paired shots to preserve characters, lighting, and mood between scenes. ( Soon I will explain what tools I created that can manage classification and caption of data when you have more than 10 000 of items, using workers and a total new way to classify data ) . Built for storytellers working with ComfyUI or other diffusers pipe ;) ! ComfyUI

66,941 просмотров

🧮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 yesterday

🧮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 yesterday

69,609 просмотров

Single image to animation update with ComfyUI ! Finally only using sdxl to keep faces coherence, but still the mess haha. Promise I will share soon the workflow, still want to make it better ! Still using LLM to describe the image and instantid ( also why i dont use SD 1.5 ) #AI #AIArtwork #Stablediffusion #aivideo

Single image to animation update with ComfyUI ! Finally only using sdxl to keep faces coherence, but still the mess haha. Promise I will share soon the workflow, still want to make it better ! Still using LLM to describe the image and instantid ( also why i dont use SD 1.5 ) #AI #AIArtwork #Stablediffusion #aivideo

98,787 просмотров

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 ?

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 ?

43,968 просмотров

🚀 Update Next Scene V2 only 10 days after last version, now live on Hugging Face 👉 🎬 A LoRA made for Qwen Image Edit 2509 that lets you create seamless cinematic “next shots” — keeping the same characters, lighting, and mood. I trained this new version on thousands of paired cinematic shots to make scene transitions smoother, more emotional, and real. 🧠 What’s new: • Much stronger consistency across shots • Better lighting and character preservation • Smoother transitions and framing logic • No more black bar artifacts Built for storytellers using ComfyUI or any diffusers pipeline. Just use “Next Scene:” and describe what happens next , the model keeps everything coherent. 🧩 Try it directly in ComfyUI, or check the thread to launch it on fal . Open-source, no restrictions, made for filmmakers, animators, and dreamers. ComfyUI #AIcinema #LoRA #Flux #Qwen #ComfyUI #AIart #GenerativeVideo you can test on comfyui or to try on you can go here : and use my lora link : start your prompt with "Next Scene:" and lets go !!

🚀 Update Next Scene V2 only 10 days after last version, now live on Hugging Face 👉 🎬 A LoRA made for Qwen Image Edit 2509 that lets you create seamless cinematic “next shots” — keeping the same characters, lighting, and mood. I trained this new version on thousands of paired cinematic shots to make scene transitions smoother, more emotional, and real. 🧠 What’s new: • Much stronger consistency across shots • Better lighting and character preservation • Smoother transitions and framing logic • No more black bar artifacts Built for storytellers using ComfyUI or any diffusers pipeline. Just use “Next Scene:” and describe what happens next , the model keeps everything coherent. 🧩 Try it directly in ComfyUI, or check the thread to launch it on fal . Open-source, no restrictions, made for filmmakers, animators, and dreamers. ComfyUI #AIcinema #LoRA #Flux #Qwen #ComfyUI #AIart #GenerativeVideo you can test on comfyui or to try on you can go here : and use my lora link : start your prompt with "Next Scene:" and lets go !!

43,366 просмотров

First time using Magic Animate at @dogstudio ! I created my own Dense Pose using Cinema 4D, I used ComfyUI , SDXL and controlnet, to generate visual. And finally MagicAnimate for the result. I think face are not good yet, but body are pretty interesting ;) !

First time using Magic Animate at @dogstudio ! I created my own Dense Pose using Cinema 4D, I used ComfyUI , SDXL and controlnet, to generate visual. And finally MagicAnimate for the result. I think face are not good yet, but body are pretty interesting ;) !

76,023 просмотров

🍌 Just released NanoBanana Pro LoRA Dataset Generator with fal Finally an easy way to create training datasets for: • Flux 2 • Z-Image • Qwen Image Edit • Any image-to-image model ✨ Uses Nano Banana Pro API on fal 🌐 100% browser-based - no server needed ⚡ Parallel generation for speed 🔗 Try it live: 💻 Code:

🍌 Just released NanoBanana Pro LoRA Dataset Generator with fal Finally an easy way to create training datasets for: • Flux 2 • Z-Image • Qwen Image Edit • Any image-to-image model ✨ Uses Nano Banana Pro API on fal 🌐 100% browser-based - no server needed ⚡ Parallel generation for speed 🔗 Try it live: 💻 Code:

30,206 просмотров

"Hand-drawn sketch → full 3D WebGL experience ✨ (Made with Claude Code and fal ) Play here 👇 60% my craft: drawing, C4D, Three.js shaders, baking 20% Claude Code 20% Image model + Hunyuan 3D AI doesn't replace creativity, it amplifies it. #threejs #WebGL #creativecoding #fal #ClaudeCode

"Hand-drawn sketch → full 3D WebGL experience ✨ (Made with Claude Code and fal ) Play here 👇 60% my craft: drawing, C4D, Three.js shaders, baking 20% Claude Code 20% Image model + Hunyuan 3D AI doesn't replace creativity, it amplifies it. #threejs #WebGL #creativecoding #fal #ClaudeCode

19,358 просмотров

More coming soon ! I manage to integrate for the first time volumetric 3D video made with Kartel.ai inside the AI world generated in gaussian splatting by World Labs !! I coded all in three.js! And it's possible to integrate elements on the fly ;) And so you can imagine soon what we will produce with that en AI : consistency of character and environment, relighting etc...

More coming soon ! I manage to integrate for the first time volumetric 3D video made with Kartel.ai inside the AI world generated in gaussian splatting by World Labs !! I coded all in three.js! And it's possible to integrate elements on the fly ;) And so you can imagine soon what we will produce with that en AI : consistency of character and environment, relighting etc...

33,984 просмотров

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 !

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 !

23,066 просмотров

✨ Introducing ComfyUI-8iPlayer: Seamlessly integrate 8i volumetric videos into your AI workflows! Load holograms, animate cameras, capture frames, and feed them to your favorite AI models. The future of 3D content creation is here! Developed by me for Kartel.ai 🚀 Note: There might be a few bugs, but I hope people can play with it! #AI #ComfyUI #Hologram

✨ Introducing ComfyUI-8iPlayer: Seamlessly integrate 8i volumetric videos into your AI workflows! Load holograms, animate cameras, capture frames, and feed them to your favorite AI models. The future of 3D content creation is here! Developed by me for Kartel.ai 🚀 Note: There might be a few bugs, but I hope people can play with it! #AI #ComfyUI #Hologram

21,036 просмотров

Fully Made in AI with wonder dynamics and ComfyUI #AI #3D #Integration #AIVIDEO #GenAI

Fully Made in AI with wonder dynamics and ComfyUI #AI #3D #Integration #AIVIDEO #GenAI

19,740 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Tesla showed the new Roadster hanging upside down 67 ft in the air. Nobody asked the passengers. So I built a simulator. haaha

Tesla showed the new Roadster hanging upside down 67 ft in the air. Nobody asked the passengers. So I built a simulator. haaha

54,433 просмотров • 1 день назад

I did this with GPT-6 Astra and a modify version of H3 Max Director from fal , still in prototype for this ( little chunk )

I did this with GPT-6 Astra and a modify version of H3 Max Director from fal , still in prototype for this ( little chunk )

509,583 просмотров • 1 месяц назад

Creating game and modifying live with AI ! Ok the future of gaming is not modding, but live modding !! I modded my game live with fal, just by talking to it, its creating each asset in live and changing the game ! "Give me a paper dragon." It's built and flying over the city. "Turn every train into a giant snail." Done. "New game." And I'm somewhere else entirely. Every model, texture and sound is generated while I play. And the game itself? Built entirely from assets generated on fal.

Creating game and modifying live with AI ! Ok the future of gaming is not modding, but live modding !! I modded my game live with fal, just by talking to it, its creating each asset in live and changing the game ! "Give me a paper dragon." It's built and flying over the city. "Turn every train into a giant snail." Done. "New game." And I'm somewhere else entirely. Every model, texture and sound is generated while I play. And the game itself? Built entirely from assets generated on fal.

14,650 просмотров • 3 дней назад

Just incredible work of the team at fal !! you can test it here :

Just incredible work of the team at fal !! you can test it here :

105,821 просмотров • 1 месяц назад

30s film with seedance 2.5 on fal from 3d made with Blender and Codex Skills for Blender + fal to make the same are available in thread

30s film with seedance 2.5 on fal from 3d made with Blender and Codex Skills for Blender + fal to make the same are available in thread

67,292 просмотров • 2 месяцев назад

A tiny demo of what I am gonna show today at genmedia conf from fal wiht h3 max director and reference to video, and also possible link with robotics (more to come about that and other models used) All the code will be available at the end of the day on my X

A tiny demo of what I am gonna show today at genmedia conf from fal wiht h3 max director and reference to video, and also possible link with robotics (more to come about that and other models used) All the code will be available at the end of the day on my X

27,551 просмотров • 24 дней назад

I trained an open-source LoRA for MiniMax H3: Realism People. weights are open. and the exact trainer I used is now available to everyone on fal Lora Link : Trainer :

I trained an open-source LoRA for MiniMax H3: Realism People. weights are open. and the exact trainer I used is now available to everyone on fal Lora Link : Trainer :

66,972 просмотров • 2 месяцев назад

After the first live stream AI created by Rehan Sheikh and Alex Matthews , here the first movie of 1h30 !!! fully generated by itself with consistent style and consistent character, much more to come on fal !!! would need a lot of edit and cut, but I wanted to show the raw result. I am working much more now on consistent environment as well to make this much better. To give your more insight this is based on minimax h3 with a train lora that was only train on 15s of data ! So a single movie could allow you to generate a full movie or much more. Working on that and if I see people interested, I could make it available !

After the first live stream AI created by Rehan Sheikh and Alex Matthews , here the first movie of 1h30 !!! fully generated by itself with consistent style and consistent character, much more to come on fal !!! would need a lot of edit and cut, but I wanted to show the raw result. I am working much more now on consistent environment as well to make this much better. To give your more insight this is based on minimax h3 with a train lora that was only train on 15s of data ! So a single movie could allow you to generate a full movie or much more. Working on that and if I see people interested, I could make it available !

43,171 просмотров • 1 месяц назад

An 8-minute animated film . Generated in 14 minutes. Crazy ! very soon and only on fal ! ( lora made for this in 1930 style Fleischer Studios for that will be share as well very soon )

An 8-minute animated film . Generated in 14 minutes. Crazy ! very soon and only on fal ! ( lora made for this in 1930 style Fleischer Studios for that will be share as well very soon )

42,603 просмотров • 1 месяц назад

, 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

, 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

99,185 просмотров • 5 месяцев назад

Releasing STUDIO 1939, my hand-painted, golden-age animation LoRA for minimax H3, open weight ! This 5-minute film? Every shot in it was generated in under 4 minutes total. Faster than it plays. The LoRA is available now. And the turbo H3 model available very soon on fal ( but you can already use it on normal endpoint )

Releasing STUDIO 1939, my hand-painted, golden-age animation LoRA for minimax H3, open weight ! This 5-minute film? Every shot in it was generated in under 4 minutes total. Faster than it plays. The LoRA is available now. And the turbo H3 model available very soon on fal ( but you can already use it on normal endpoint )

32,781 просмотров • 1 месяц назад

Its coming tomorrow and no, its not seedance :), it should follow and respect much more the 3d input render, and its gonna be open source !

Its coming tomorrow and no, its not seedance :), it should follow and respect much more the 3d input render, and its gonna be open source !

59,379 просмотров • 3 месяцев назад

training a video model to teach sign language , coming soon !

training a video model to teach sign language , coming soon !

10,154 просмотров • 16 дней назад

Single prompt using Fable in Blender.. Soon result with our new version of the model 3dToReal on fal

Single prompt using Fable in Blender.. Soon result with our new version of the model 3dToReal on fal

44,692 просмотров • 3 месяцев назад

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 🙏

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 🙏

66,109 просмотров • 7 месяцев назад

Last homage of the heroes of my childhood :) Made with gpt 6 , fal and three.js

Last homage of the heroes of my childhood :) Made with gpt 6 , fal and three.js

12,240 просмотров • 1 месяц назад

None of the video gen models do a real CRT terminal animation look. So I trained my own with fal. CRT-anim : open-source LoRA for LTX-2.3 22B. Runs on fal + ComfyUI.

None of the video gen models do a real CRT terminal animation look. So I trained my own with fal. CRT-anim : open-source LoRA for LTX-2.3 22B. Runs on fal + ComfyUI.

41,911 просмотров • 6 месяцев назад

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).

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).

89,083 просмотров • 1 год назад

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.

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.

50,520 просмотров • 8 месяцев назад

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 :)

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 :)

93,560 просмотров • 1 год назад