Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
RTX 3090 40 FPS Diffusion
Learn how to overcome technical challenges of live video‑to‑video pipelines, enabling real‑time diffusion that streams over 40 images per second on RTX 3090.
In this talk, I will quickly walk you through the technical difficulties encountered while building a live video-to-video pipeline and its implications for the interactive and immersive art.
- PyTorchPyTorch is the open-source machine learning framework: it provides a Python-first tensor library with strong GPU acceleration and a dynamic computation graph for building deep neural networks.PyTorch, developed by Meta AI, is a premier open-source deep learning framework favored in both research and production environments. Its core is a powerful tensor library (like NumPy) optimized for GPU acceleration, delivering 50x or greater speedups for complex computations. The key differentiator is its 'Pythonic' design and dynamic computation graph (eager execution), which allows for rapid prototyping and simplified debugging compared to static-graph frameworks. Leveraging its Autograd system for automatic differentiation, practitioners build and train models for computer vision and NLP; major companies like Tesla (Autopilot) and Microsoft utilize PyTorch for critical AI applications.
- Stable DiffusionStable Diffusion is a latent text-to-image diffusion model: it generates detailed, photo-realistic imagery from a text prompt.Stable Diffusion is a generative AI model, developed by Stability AI, that transforms text descriptions into high-resolution digital images. Released in 2022, this deep learning system is an open-source latent diffusion model (LDM), a key distinction from proprietary competitors. It requires minimal hardware (e.g., a modest GPU with 2.4 GB VRAM) for local operation, democratizing high-end image synthesis. Beyond text-to-image generation, the technology supports image-to-image translations, inpainting (editing within an image), and outpainting (extending an image).
Related projects
streamdiffusion in flair ai realtime feature
San Francisco
Pipelining intermediate tensors accelerates real-time image generation for product photoshoots by effectively batching single-user inputs on the GPU.
Generate precise and coherent images on your laptop with Stable Diffudion
Paris
This talk demonstrates controlling poses, styles, and character consistency using Stable Diffusion and ComfyUI for customized, inclusive image…
Creative AI Off-Roading: Unconventional Workflows for Imaginative Collaboration
Prague
Explore unconventional AI workflows that prioritize creativity and experimentation, demonstrating how blended AI tools can generate imaginative art…
Renderer
London
Demonstration of a prototype pipeline that integrates traditional CG software with stable diffusion models, creating a novel rendering…
Hacking Stable Diffusion to generate audioreactive animations in the browser
Berlin
Learn how to combine Stable Diffusion with real-time audio analysis to create browser‑based, AI‑generated music videos, covering the…
AI for Analyzing Trends
Prague
Learn how to create an AI-driven blog that extracts Google and Amazon trend data, uses Python and AWS,…