# ComfyUI Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/comfyui
> Markdown URL: https://aitinkerers.org/technologies/comfyui.md
> Technology record last updated: 2026-02-25T11:17:20Z
> Generated: 2026-09-20T19:46:59Z

ComfyUI is the premier open-source, node-based interface for building and executing highly customized generative AI workflows (Stable Diffusion, video, 3D).

ComfyUI is your foundational, open-source engine for visual generative AI, operating on a powerful node-based interface. This architecture gives users total control: you visually construct complex AI pipelines—connecting components like samplers, models, and custom nodes (e.g., Animatediff, IPAdapter)—to achieve precise, reproducible results. Unlike simpler UIs, ComfyUI excels in advanced Stable Diffusion workflows, video generation, and 3D asset creation, maximizing hardware efficiency and allowing for low-level parameter adjustments. It is the flexible operating system for the next generation of AI artists and developers.

- Official technology site: https://comfy.org
- Public AI Tinkerers demos and talks: 13
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Built a Browser Game With a Team of AI Agents, and Here's Everything That Broke](https://dubai.aitinkerers.org/talks/rsvp_ykDyOGchyI8)

The Crawl is a cel shaded isometric action RPG that runs entirely in the browser, a fan game of Dungeon Crawler Carl, and I built almost all of it by orchestrating a small team of AI coding agents rather than writing the code myself. In the demo I'll play the opening live, a motion comic cold open that hands off straight into in engine gameplay, then pull back the curtain on how it was actually made. I'll show the running game, the GitHub repo, the local content pipeline that turns concept art into rigged 3D characters, the handoff files the agents used to coordinate, and the git history that quietly acted as the message bus between them. It is a real working system, not a mockup, and most of the interesting parts are the places where it went wrong first.

- Event context: AI Tinkerers Dubai — August Demo Day — 2026-08-08 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_ykDyOGchyI8

### [Hybrid AI/VFX workflow](https://montreal.aitinkerers.org/talks/rsvp_dME8XrE7GlI)

Hyprid VFX / AI pipeline. Generative AI used in a controlled way to enchance film footage. The "Hockeyville" project is a hybrid VFX production for a KRAFT commercial that utilizes local Generative AI to transform live-action urban footage into a frozen landscape. https://vimeo.com/1173898332

- Event context: AI Tinkerers Montreal - March Demo Night — 2026-03-24 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_dME8XrE7GlI

### [StableGen - diffusion powered texturing within Blender](https://prague.aitinkerers.org/talks/rsvp_5HqwtbOGNaU)

This will be a 5-minute live demonstration of StableGen, a Blender plugin designed for AI-driven 3D texturing. I will begin with a standard untextured 3D model in Blender and walk through a typical texturing workflow. First, I'll set up the camera viewpoints and assign a text prompt for the desired texture. I will then initiate the generation process, which runs asynchronously in the background. While the plugin is working, I will show the key artifacts and workflows it manages, including the exported ControlNet images (like depth maps) used for geometric guidance and the dynamically generated ComfyUI workflow graph sent to the backend. I will then show the final output images generated for each viewpoint. To conclude, I will show the final, fully-textured 3D model in the Blender viewport and point to the complex material node tree that StableGen automatically built to seamlessly blend all the individual textures together. I could also make it interactive by having the audience choose what to generate. Note: I could also go through the code, but as the project is pretty large, I don't think 5 minutes is nearly enough to even start diving into that.

- Event context: 🍂 AI Tinkerers Prague – October 2025 Meetup — 2025-10-23 — Prague
- Public talk page: https://prague.aitinkerers.org/talks/rsvp_5HqwtbOGNaU

### [Controllable AI Video Generation: Wan 2.1 & ComfyUI](https://la.aitinkerers.org/talks/rsvp_wTyb6qTHp6Q)

Wan2.1 is an open-source video generation and control project developed by Alibaba team. It introduces innovative control codes mechanisms combined with deep learning and multimodal conditional inputs to generate high-quality videos that conform to preset control conditions. The project focuses on precisely guiding generated video content through multimodal control conditions. Playbook 3D is building a unified platform and custom interface around ComfyUI to ensure security, scalability, and reusability across productions.

- Event context: June 9th - LA AI Tinkerers Meetup & Demos — 2025-06-10 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_wTyb6qTHp6Q

### [Virtual Try-On: Video Model Magic](https://hong-kong.aitinkerers.org/talks/rsvp_nsxvntR9_Ok)

Explore the future of fashion with cutting-edge video models that power seamless virtual try-on experiences. This technology blends AI precision and real-time visuals, letting users try clothes virtually with stunning accuracy and ease.

- Event context: AI Tinkerers - Hong Kong Meetup (March) - Art Month & International Women's Day! — 2025-03-20 — Hong Kong
- Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_nsxvntR9_Ok

### [Bringing Agents To Life](https://denver-boulder.aitinkerers.org/talks/rsvp_j5no5HCo0Qw)

An alpha demo and theory of how the Agent SPE is using Livepeer to bring autonomous live-streaming to AI Agents.

- Event context: Open Source & Creative AI: Using ComfyUI for Real Time Video AI — 2025-02-25 — Denver
- Public talk page: https://denver-boulder.aitinkerers.org/talks/rsvp_j5no5HCo0Qw

### [Day Dream and ComfyStream](https://denver-boulder.aitinkerers.org/talks/rsvp_oJjm_AlQ-Ck)

I will demo the new AI application released by Livepeer, Day Dream. I will also showcase the open source workflow development tool we used to create Day Dream, called ComfyStream.

- Event context: Open Source & Creative AI: Using ComfyUI for Real Time Video AI — 2025-02-25 — Denver
- Public talk page: https://denver-boulder.aitinkerers.org/talks/rsvp_oJjm_AlQ-Ck

### [Generate precise and coherent images on your laptop with Stable Diffudion](https://paris.aitinkerers.org/talks/rsvp_oVGgE1beWr0)

This demo will show how to control poses, styles, and character consistency for use cases like yoga pose visualization (feedback from my ongoing work for my Yoga website www.yogarkana.com) with the local use of Stable Diffusion models and advanced ComfyUI workflows. Learn how to customize Stable Diffusion workflows to meet their your own creative, commercial, or inclusive design needs.

- Event context: AI Tinkerers - Paris Meetup on January 30th — 2025-01-30 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_oVGgE1beWr0

### [Real Time Video AI with ComfyUI](https://nyc.aitinkerers.org/talks/rsvp_97qRm28Pj10)

ComfyStream is a framework that helps developers apply AI to real time video workflows, using ComfyUI as the backend. This tool can help with content creation, real time communication, and real time video understanding.

- Event context: AI Tinkerers - New York City - December 2024 Meetup — 2024-12-12 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_97qRm28Pj10

### [GOWONU: A ChatGPT Survival Horror Game](https://toronto.aitinkerers.org/talks/rsvp_577lfKqD4lA)

GOWONU is an AI-driven choose your own adventure survival horror game created inside ChatGPT as an app, where every room, every choice, and every threat is generated in real time chosen by the user. Trained on my document of the GOWONU game i'm continuing to build, using DALL-E with ChatGPT, the game creates a procedurally generated, cursed apartment complex inspired by Kowloon’s dense architecture. Players navigate shifting environments, discover eerie clues, and confront terrifying entities—all while trying to maintain their sanity. No two experiences are the same. In this demo, I’ll show how GOWONU integrates AI to drive unpredictable storytelling and visuals using a customized ChatGPT app based on the concept and story developed by Artist's Journey and Artlink. Utilizing AI with ChatGPT doesn’t just enhance the game—it creates the world you explore, the threats you face, and the eerie atmosphere that changes with each decision. You'll see how AI-generated environments keep players on edge, with procedurally designed rooms, cryptic photos, and choices that matter. And how this is the first step into more immersive gameplay.

- Event context: AI Tinkerers Toronto - Spooky Botober Meetup at Mozilla HQ — 2024-10-30 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_577lfKqD4lA

### [Gamifying Educational Experiences](https://atlanta.aitinkerers.org/talks/rsvp_rc1mg26o7jM)

Surfing on Entropy is a fictional story platform that uses AI-driven educational onboarding side quests as a way to open new pieces of educational content within the narrative experience. You and your team use logic to solve enigmas to unlock new pieces of content depending on the NFTs you've collected in your wallet or received to your email from the experience.

- Event context: AI Tinkerers Atlanta September Meetup — 2024-09-18 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_rc1mg26o7jM

### [Flux, a new generation of Image Generation Models](https://boston.aitinkerers.org/talks/rsvp_UNy9T277gyY)

The Flux Generation 1 models have taken the image generation community by storm, revolutionizing AI image creation. Text to image has never been easier, and the image to image possibilities are only starting to be explored. How can someone jump into the image generation scene? This talk will cover local tools like ComfyUI and online tools like Replicate. It will also briefly cover LoRAs and what they can do for refined image generation. I don't have a project URL for this yet, but I'm planning to build image generation using Flux into my professional website because some of the APIs are so cheap.

- Event context: August 2024 Meetup at Æthos — 2024-08-26 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_UNy9T277gyY

### [Stable Diffusion - Transform your casual photos into professional portraits.](https://singapore.aitinkerers.org/talks/rsvp_AkHCI1PlIi4)

This demo utilizes the ComfyUI workflow with an open-source Stable Diffusion model to achieve stunning results.

- Event context: AI Tinkerers Singapore: Inaugural Meetup - August 2nd, 2024 — 2024-08-02 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_AkHCI1PlIi4

## Related Technologies

- [Stable Diffusion](https://aitinkerers.org/technologies/stable-diffusion) ([Markdown](https://aitinkerers.org/technologies/stable-diffusion.md)) — 32 public demos
- [Blender](https://aitinkerers.org/technologies/blender) ([Markdown](https://aitinkerers.org/technologies/blender.md)) — 4 public demos
- [ComfyStream](https://aitinkerers.org/technologies/comfystream) ([Markdown](https://aitinkerers.org/technologies/comfystream.md)) — 2 public demos
- [ControlNet](https://aitinkerers.org/technologies/controlnet) ([Markdown](https://aitinkerers.org/technologies/controlnet.md)) — 6 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [Livepeer](https://aitinkerers.org/technologies/livepeer) ([Markdown](https://aitinkerers.org/technologies/livepeer.md)) — 2 public demos
- [LoRA](https://aitinkerers.org/technologies/lora) ([Markdown](https://aitinkerers.org/technologies/lora.md)) — 17 public demos
- [APIs](https://aitinkerers.org/technologies/apis) ([Markdown](https://aitinkerers.org/technologies/apis.md)) — 19 public demos
- [Artist's Journey](https://aitinkerers.org/technologies/artist-s-journey) ([Markdown](https://aitinkerers.org/technologies/artist-s-journey.md)) — 1 public demo
- [Blockcerts](https://aitinkerers.org/technologies/blockcerts) ([Markdown](https://aitinkerers.org/technologies/blockcerts.md)) — 1 public demo
- [ChatGPT](https://aitinkerers.org/technologies/chatgpt) ([Markdown](https://aitinkerers.org/technologies/chatgpt.md)) — 83 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 173 public demos
- [Claude-3](https://aitinkerers.org/technologies/claude-3) ([Markdown](https://aitinkerers.org/technologies/claude-3.md)) — 110 public demos
- [DALL-E](https://aitinkerers.org/technologies/dall-e) ([Markdown](https://aitinkerers.org/technologies/dall-e.md)) — 6 public demos
- [DaVinci Resolve](https://aitinkerers.org/technologies/davinci-resolve) ([Markdown](https://aitinkerers.org/technologies/davinci-resolve.md)) — 1 public demo
- [Diffusion models](https://aitinkerers.org/technologies/diffusion-models) ([Markdown](https://aitinkerers.org/technologies/diffusion-models.md)) — 5 public demos
- [ElizaOS](https://aitinkerers.org/technologies/elizaos) ([Markdown](https://aitinkerers.org/technologies/elizaos.md)) — 1 public demo
- [Flux Generation 1](https://aitinkerers.org/technologies/flux-generation-1) ([Markdown](https://aitinkerers.org/technologies/flux-generation-1.md)) — 1 public demo