# Diffusion models Projects at AI Tinkerers > Canonical HTML: https://aitinkerers.org/technologies/diffusion-models > Markdown URL: https://aitinkerers.org/technologies/diffusion-models.md > Technology record last updated: 2026-02-26T21:35:41Z > Generated: 2026-09-21T10:49:19Z Generative AI models that synthesize high-fidelity data (e.g., images, audio) by learning to iteratively reverse a fixed, step-by-step noise addition process. Diffusion models operate on a two-part mechanism: a forward diffusion process and a reverse sampling process. The forward process systematically corrupts training dataβ€”like a clean imageβ€”by adding Gaussian noise over hundreds or thousands of steps until only pure noise remains. The model then trains a neural network, typically a U-Net, to master the reverse process: iteratively predicting and removing that noise to reconstruct the original data distribution. This denoising capability, starting from a random noise seed, allows for the generation of entirely new, high-quality samples. Key commercial examples, like OpenAI's DALL-E 2 and Stability AI's Stable Diffusion, leverage this core technology for state-of-the-art text-to-image synthesis. - Official technology site: https://en.wikipedia.org/wiki/Diffusion_model - Public AI Tinkerers demos and talks: 5 - Result page: 1 of 1 ## Recent Public Talks and Demos ### [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: πŸ‚ AI Tinkerers Prague – October 2025 Meetup β€” 2025-10-23 β€” Prague - Public talk page: https://prague.aitinkerers.org/talks/rsvp_5HqwtbOGNaU ### [Can you tell? Works by Human artist vs AI artist](https://hong-kong.aitinkerers.org/talks/rsvp_Egn5P7m9fmI) ⁠In this demo, Helen, the speaker, will pose a thought-provoking question: "Works by Human Artists vs. AI Artists." She will then share her experiences as a traditional medium artist who uses AI to enhance her work. Additionally, she will discuss her community initiatives with students focused on AI creation. - Event context: AI Tinkerers - Hong Kong Meetup (March) - Art Month & International Women's Day! β€” 2025-03-20 β€” Hong Kong - Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_Egn5P7m9fmI ### [The Morphing Machine: AI-Generated Human-Animal Hybrids](https://toronto.aitinkerers.org/talks/rsvp_tEUi92q3o6o) This demo showcases a custom AI model built for Netflix's Sweet Tooth, designed to generate images of hybrid human-animal characters like those seen in the series. Using a diffusion-based neural network, the model merges human and animal features to create lifelike, imaginative hybrids. I’ll walk through the technical challenges, including dataset preparation and fine-tuning the model for creative yet accurate results. This project demonstrates how AI can be applied to character design in entertainment. - Event context: AI Tinkerers Toronto - Spooky Botober Meetup at Mozilla HQ β€” 2024-10-30 β€” Toronto - Public talk page: https://toronto.aitinkerers.org/talks/rsvp_tEUi92q3o6o ### [Exploiting the Signal-Leak Bias in Diffusion Models](https://lausanne.aitinkerers.org/talks/rsvp_vhQGhvfVwH4) I will show a Jupyter Notebook demo of my research work on a bias present in most diffusion models for image generation, especially Stable Diffusion (v1 and v2). I will show that there is currently a discrepancy between training and inference processes in these models, and show how to fix and exploit this discrepancy to gain more control over generated images. The method does not require any additional training and can be applied directly during inference. Project page: https://ivrl.github.io/signal-leak-bias/ Research paper: https://arxiv.org/abs/2309.15842 Github: https://github.com/IVRL/signal-leak-bias - Event context: AI Tinkerers Lausanne Inaugural June Meetup β€” 2024-06-24 β€” Lausanne - Public talk page: https://lausanne.aitinkerers.org/talks/rsvp_vhQGhvfVwH4 ### [streamdiffusion in flair ai realtime feature](https://sf.aitinkerers.org/talks/rsvp_iMQqQpJR_RU) accelerate image generation by pipelining your tensors with streamdiffusion! we optimize our real-time product photoshoot preview by basically storing intermediate tensors in the diffusion process so that we effectively are batching our inputs even when only a single user is on a gpu machine at a time. - Event context: AI Tinkerers - San Francisco - April 2024 Meetup β€” 2024-04-30 β€” San Francisco - Public talk page: https://sf.aitinkerers.org/talks/rsvp_iMQqQpJR_RU ## Related Technologies - [arXiv](https://aitinkerers.org/technologies/arxiv) ([Markdown](https://aitinkerers.org/technologies/arxiv.md)) β€” 9 public demos - [Blender](https://aitinkerers.org/technologies/blender) ([Markdown](https://aitinkerers.org/technologies/blender.md)) β€” 4 public demos - [Canva](https://aitinkerers.org/technologies/canva) ([Markdown](https://aitinkerers.org/technologies/canva.md)) β€” 2 public demos - [CapCut](https://aitinkerers.org/technologies/capcut) ([Markdown](https://aitinkerers.org/technologies/capcut.md)) β€” 1 public demo - [ComfyUI](https://aitinkerers.org/technologies/comfyui) ([Markdown](https://aitinkerers.org/technologies/comfyui.md)) β€” 13 public demos - [ControlNet](https://aitinkerers.org/technologies/controlnet) ([Markdown](https://aitinkerers.org/technologies/controlnet.md)) β€” 6 public demos - [Dataset preparation](https://aitinkerers.org/technologies/dataset-preparation) ([Markdown](https://aitinkerers.org/technologies/dataset-preparation.md)) β€” 1 public demo - [Fine-tuning](https://aitinkerers.org/technologies/fine-tuning) ([Markdown](https://aitinkerers.org/technologies/fine-tuning.md)) β€” 20 public demos - [Flair AI](https://aitinkerers.org/technologies/flair-ai) ([Markdown](https://aitinkerers.org/technologies/flair-ai.md)) β€” 2 public demos - [GitHub](https://aitinkerers.org/technologies/github) ([Markdown](https://aitinkerers.org/technologies/github.md)) β€” 74 public demos - [GPU](https://aitinkerers.org/technologies/gpu) ([Markdown](https://aitinkerers.org/technologies/gpu.md)) β€” 12 public demos - [Image generation](https://aitinkerers.org/technologies/image-generation) ([Markdown](https://aitinkerers.org/technologies/image-generation.md)) β€” 4 public demos - [IPAdapter](https://aitinkerers.org/technologies/ipadapter) ([Markdown](https://aitinkerers.org/technologies/ipadapter.md)) β€” 1 public demo - [Jupyter notebook](https://aitinkerers.org/technologies/jupyter-notebook) ([Markdown](https://aitinkerers.org/technologies/jupyter-notebook.md)) β€” 13 public demos - [LLM](https://aitinkerers.org/technologies/llm) ([Markdown](https://aitinkerers.org/technologies/llm.md)) β€” 123 public demos - [Stable Diffusion](https://aitinkerers.org/technologies/stable-diffusion) ([Markdown](https://aitinkerers.org/technologies/stable-diffusion.md)) β€” 32 public demos - [Streamdiffusion](https://aitinkerers.org/technologies/streamdiffusion) ([Markdown](https://aitinkerers.org/technologies/streamdiffusion.md)) β€” 1 public demo - [Suno](https://aitinkerers.org/technologies/suno) ([Markdown](https://aitinkerers.org/technologies/suno.md)) β€” 2 public demos