AInVFX

AInVFX Contact information, map and directions, contact form, opening hours, services, ratings, photos, videos and announcements from AInVFX, Education Website, Huntsville, ON.

We bring AI to the Animation and Visual Effects industry in a human way: Empowering artistsโ€™ creativity, driving studiosโ€™ efficiency, crafting the future of storytelling

https://www.youtube.com/shorts/U7pI2-Dpm1wGive it one shot from a film. Shot-to-Set breaks the shot down, works out who ...
09/21/2026

https://www.youtube.com/shorts/U7pI2-Dpm1w

Give it one shot from a film. Shot-to-Set breaks the shot down, works out who is in it and what surrounds them, rebuilds all of it in 3D and assembles the scene in Unreal Engine. Then you put on a VR headset and you are standing on the set.

Ersan Musa, Previs Supervisor, built it as his project in cohort 1 of our Generative AI Bootcamp for Film and TV. It is a chain of more than a dozen ComfyUI workflows connected with n8n, running locally: the shot is split into frames and audio, Qwen analyses the frames and browses the web to identify the actors, the wardrobe, the vehicles and the set, then each character is rebuilt from a portrait and several views, the set is captured as a Gaussian splat, and everything is assembled in Unreal Engine. Three modes: automatic, assisted (the tool stops and asks you to confirm who is in the shot) and manual.

That is how the course works: you bring one production case, you build it on ComfyUI across 20 live sessions with two instructors, and a jury of working AI professionals reviews it twice. Cohort 2 starts on 2 October 2026, cohort 3 on 6 January 2027.

๐Ÿ“ฐ Read the full article: https://www.ainvfx.com/blog/shot-to-set-from-one-film-shot-to-a-set-you-can-visit-in-vr-built-in-the-bootcamp/
๐ŸŽ“ Enroll in the bootcamp: https://www.ainvfx.com/bootcamp/
๐Ÿ’ฌ Questions? Join our Discord: https://discord.gg/6CKSa3b5ks
๐ŸŒ Website: https://www.ainvfx.com

Music by Liborio Conti (https://www.youtube.com/c/liborioconti) - "Ukulele Life" (creative commons music cc-by)

Give it one shot from a film. Shot-to-Set breaks the shot down, wor...

https://youtube.com/shorts/chpONr4ZofUEveryone on a project has ideas for a shot. Fewer people can draw them. Julien Cha...
09/19/2026

https://youtube.com/shorts/chpONr4ZofU

Everyone on a project has ideas for a shot. Fewer people can draw them. Julien Chateau built a tool that makes a rough sketch enough: draw where the characters and the camera go, add one line of text, and get back a clean storyboard frame that keeps your framing and your poses.

Julien Chateau, CG Instructor, built it as his project in cohort 1 of our Generative AI Bootcamp for Film and TV. It runs in the browser and calls ComfyUI workflows in the background. In this short: a storyboard you can reorder shot by shot; a rough sketch turned into a clean frame with Qwen Image Edit and a LoRA Julien trained on 44 sketch-and-drawing pairs; outpainting to bring a frame to the project's format; and character swap from a model sheet, to replace a character or correct one. It is made for artists who are not comfortable with drawing, and for those who want faster iterations with the same quality on every frame. Nothing is generated without a drawing first.

That is how the course works: you bring one production case, you build it on ComfyUI across 20 live sessions with two instructors, and a jury of working AI professionals reviews it twice. Cohort 2 starts on 2 October 2026, cohort 3 on 6 January 2027.

๐Ÿ“ฐ Read the full article: https://www.ainvfx.com/blog/from-rough-sketch-to-clean-storyboard-a-comfyui-tool-built-in-the-bootcamp/
๐ŸŽ“ Enroll in the bootcamp: https://www.ainvfx.com/bootcamp/
๐Ÿ’ฌ Questions? Join our Discord: https://discord.gg/6CKSa3b5ks
๐ŸŒ Website: https://www.ainvfx.com

Music by Liborio Conti (https://www.youtube.com/c/liborioconti) - "Skyline" (creative commons music cc-by)

Everyone on a project has ideas for a shot. Fewer people can draw t...

https://youtube.com/shorts/I3z20F3Tf60Type a prompt inside Unreal Engine and get a 3D asset in your scene. Frame a shot,...
09/19/2026

https://youtube.com/shorts/I3z20F3Tf60

Type a prompt inside Unreal Engine and get a 3D asset in your scene. Frame a shot, send it to ComfyUI, and get it back as a watercolour or a comic book style, projected onto the geometry. Once the projection is applied, you move around the scene in real time.

Kevin Bertelli built both during cohort 1 of our Generative AI Bootcamp for Film and TV, the fourth of the cohort projects we share. Kevin is a CG Supervisor and a real-time specialist. Most of his work is in Unreal Engine, so he wanted the tools where he works: two Unreal plugins that talk to ComfyUI.

๐—ฃ๐—น๐˜‚๐—ด๐—ถ๐—ป ๐Ÿญ, an asset generator: Z-Image Turbo generates the concept from your prompt, you check it in the panel, and Pixal3D turns it into a mesh that loads into the scene. Quick assets to fill a previz, in about 200 seconds each. The ComfyUI server runs on a second computer, so Unreal keeps its real-time playback while the asset is being made.

๐—ฃ๐—น๐˜‚๐—ด๐—ถ๐—ป ๐Ÿฎ, camera mapping with a style transfer: capture the camera view, restyle it with Qwen Image Edit from one line of text, and project it back from the same camera. The projection is masked so nothing lands behind objects or in their shadows, several captures can cover one object, and anything the model gets wrong is painted over in Photoshop and projected on top. Change the line of text, and the scene gets another look.

Both are made for previz: fill the scene fast, give it a look, try another one without rebuilding anything.

Cohorts 2 (2 October) and 3 (6 January) are open for enrollment. Cohort 2 starts in two weeks. Link in the comments.

๐—–๐—ผ๐—บ๐—ฒ ๐—ฏ๐˜‚๐—ถ๐—น๐—ฑ ๐˜„๐—ถ๐˜๐—ต ๐˜‚๐˜€!

Type a prompt inside Unreal Engine and get a 3D asset in your scene...

https://www.youtube.com/watch?v=3t38YJYAjto&feature=youtu.beBetween humans, fear, admiration or inspiration need no expl...
09/17/2026

https://www.youtube.com/watch?v=3t38YJYAjto&feature=youtu.be

Between humans, fear, admiration or inspiration need no explanation. Explain them to a machine, and it may be impossible. Goosebumps imagines the journey of an AI learning a human emotion, and the film was itself generated by an AI.

Rudyard Cretenet, 2D Supervisor, made it during cohort 1 of our Generative AI Bootcamp for Film and TV, his first weeks ever with generative AI after many years in Nuke. Images and voice-over generated with LTX 2.5 in ComfyUI, in groups of three shots fed back into treatment passes, then edited in DaVinci Resolve. This is the film as he showed it to the final jury.

It is one of three pieces he brought to that jury. The article covers the other two: architecture studies for a Paris that never was, with Z-Image Turbo and Qwen Image Edit 2511, and test shots for a film set in Belgium, reworked with Qwen Image Edit 2511: backgrounds, sky, camera axis, focal length and clean plate, before anyone goes on set.

That is how the course works: you bring one production case, you build it on ComfyUI across 20 live sessions with two instructors, and a jury of working AI professionals reviews it twice. No prior AI experience needed. Cohort 2 starts on 2 October 2026, cohort 3 on 6 January 2027.

๐Ÿ“ฐ Read the full article: https://www.ainvfx.com/blog/from-nuke-to-comfyui-a-2d-supervisors-first-generative-ai-projects-built-in-the-bootcamp/
๐ŸŽ“ Enroll in the bootcamp: https://www.ainvfx.com/bootcamp/
๐Ÿ’ฌ Questions? Join our Discord: https://discord.gg/6CKSa3b5ks
๐ŸŒ Website: https://www.ainvfx.com

Music: "Celestial Calling (Original Mix)" by Fog Temple, licensed through Slipstream Music (https://slipstreammusic.com/tracks/22588739-8086-4faf-9e37-80a472b78283)

Between humans, fear, admiration or inspiration need no explanation...

https://youtube.com/shorts/odelUPdT5dkOpen your hand and a menu appears, then follows your hand. Hold still over an opti...
09/16/2026

https://youtube.com/shorts/odelUPdT5dk

Open your hand and a menu appears, then follows your hand. Hold still over an option to select it. You are the controller: a camera reads your hands, and ComfyUI does the rest.

Alexandre built this interactive experience as his project in cohort 1 of our Generative AI Bootcamp for Film and TV. It is made for people who have never seen a node graph. You stand in front of a screen, pick an ambience (fire, ice, storm), an avatar style (cyberpunk, manga, zombie), an environment, and how much the result should still look like you. Custom ComfyUI nodes read the we**am and turn hand gestures into values from 0 to 1. The whole interface, menus included, is built inside ComfyUI. The images are generated live, image-to-image, on a single RTX 3060.

Alexandre is a Technical Director and is part of a Fab Lab. He came to the bootcamp with one real need and left with a working installation. That is how the course works: you bring one production case, you build it on ComfyUI across 20 live sessions with two instructors, and a jury of working AI professionals reviews it twice. Cohort 2 starts on 2 October 2026, cohort 3 on 6 January 2027.

๐ŸŽ“ Enroll in the bootcamp: https://www.ainvfx.com/bootcamp/
๐Ÿ’ฌ Questions? Join our Discord: https://discord.gg/6CKSa3b5ks
๐ŸŒ Website: https://www.ainvfx.com

Music by Liborio Conti (https://www.youtube.com/c/liborioconti) - "More Power" (creative commons music cc-by)

Open your hand and a menu appears, then follows your hand. Hold sti...

https://www.youtube.com/shorts/eBAut-V1FNwPaint where the volume starts and where it ends, in flat colours, and this IC-...
09/16/2026

https://www.youtube.com/shorts/eBAut-V1FNw

Paint where the volume starts and where it ends, in flat colours, and this IC-LoRA for LTX 2.5 fills in the smoke, steam or fire and animates between your keyframes. A 5-second element takes about a minute on a laptop GPU, so it works as an art-directable stock shot generator: the shape, the colour and the timing stay yours, and nothing is simulated. Trained on 52 free-to-use Pexels clips as a teaching example for our Generative AI Bootcamp for Film and TV. The weights, the ComfyUI workflow and the painted example frames are free on Hugging Face.

๐Ÿค— Model, workflow and samples: https://huggingface.co/AInVFX/ainvfx-fluid
๐Ÿคฟ Watch the full deep dive tutorial: https://www.youtube.com/watch?v=Ho4tmJzEkIs
๐Ÿ“ฐ Read the article: https://www.ainvfx.com/blog/paint-your-fluid-simulations-a-free-ltx-2-5-ic-lora-for-smoke-and-fire-in-comfyui/
๐ŸŽ“ Learn about our upcoming bootcamps: https://www.ainvfx.com/bootcamp/

Paint where the volume starts and where it ends, in flat colours, a...

I submitted a small personal contribution to the Arca Gidan contest โ€” a 2-minute short film made entirely with open sour...
04/04/2026

I submitted a small personal contribution to the Arca Gidan contest โ€” a 2-minute short film made entirely with open source models, built around 73 of my own ink drawings.

The full training process is shared freely: the Z-Image style LoRA, the LTX-V 2.3 video LoRA, and every step in between. All open, all documented.

But honestly โ€” go look at the other submissions first. There's a lot of great work in there, and voting is open until April 6th. Watch a few, leave a score, get inspired.

๐ŸŽฌ Teaser: https://youtube.com/shorts/hq1jg6s91y0
๐ŸŽฌ Full selection: https://arcagidan.com/submissions/entry/5ca70873-e0c6-481a-96ef-5e15809451be

This teaser covers the full pipeline: training a Z-Image style LoRA for image generation, then an LTX-V 2.3 LoRA to bring it to life. The entire process โ€” da...

Address

Huntsville, ON

Website

,

Alerts

Be the first to know and let us send you an email when AInVFX posts news and promotions. Your email address will not be used for any other purpose, and you can unsubscribe at any time.

Shortcuts

Share

Category