Subvolts take Understand visual AI's progress from blurry images to intelligent tools with Black Forest Labs. Jul 2, 2026 - Developers
- Learn about flow matching and the FLUX models for practical image generation and editing workflows.
- Business
- Understand how advanced visual AI is being applied to practical tasks beyond basic image creation.
This episode features a researcher from a specialized lab discussing core technical advancements in a key AI area.
Image Generation and Visual Intelligence with Black Forest Labs
Audio streams from Daniel Whitenack and Chris Benson. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
This Practical AI episode features Dustin Podell of Black Forest Labs discussing the evolution of AI image generation. They cover the shift from diffusion to flow matching, how current models work, and their applications in image editing and visual workflows. The conversation also touches on the FLUX models, local image generation, and future directions in visual AI.
This episode explains how AI creates images, moving from early blurry pictures to today's smart tools. It covers new techniques like flow matching and how these AI models can edit photos and help with visual tasks, making AI more useful for everyday things.
This episode offers insight into the technical advancements driving AI image generation, moving beyond basic output to sophisticated visual intelligence. It is for researchers, developers, and anyone interested in the practical application of AI in visual media. The discussion on flow matching and the FLUX models provides context for how frontier labs like Google Gemini and OpenAI are pushing the boundaries of multimodal AI, particularly in image and video understanding and creation.
- HostDaniel Whitenack
- HostChris Benson
- GuestDustin PodellCo-Founder and Researcher, Black Forest Labs
- Guest: Dustin Podell, Co-Founder and Researcher at Black Forest Labs
- Show: Practical AI
- Length: 48 minutes
- Topics Covered: Evolution from diffusion to flow matching, modern image models, image editing, visual workflows, FLUX models, local image generation.
Chapters from the publisher ↗ · Transcript ↗ Key moments and transcript search come with a later piece.
How has AI image generation evolved from blurry outputs to powerful visual intelligence models? Dustin Podell, Co-Founder and Researcher at Black Forest Labs, explains the progression from diffusion to flow matching, how modern image models work, and how they're being used for image editing and practical visual workflows. The conversation also explores the FLUX family of models, running image generation locally, and where visual AI is headed next.
Featuring:
- Dustin Podell – LinkedIn
- Chris Benson – Website, LinkedIn, Bluesky, GitHub, X
- Daniel Whitenack – Website, GitHub, X
Links:
- Black Forest Labs
- Developer Dashboard
- Research Page
- FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
- Laying the Foundations for Visual Intelligence
Sponsors:
- Midwest AI Summit: Join AI practitioners on October 15 in Indianapolis for practical sessions, hands-on discussions, and real-world AI solutions. Use code PracticalAI20 to save 20% on your registration. https://midwestaisummit.com/#tickets
- Prediction Guard: A self-hosted AI control plane for running agents in high impact environments. predictionguard.com/practicalai
Upcoming Events:
- Register for upcoming webinars here!
- Midwest AI Summit 2026
- Diffusion
- Dustin Podell
- An older method for AI image generation.
- Flow Matching
- Dustin Podell
- A newer technique for AI image generation that improves visual intelligence.
44 minNarrative intelligence and the human advantage
WithReed Frerichs
47 minOpen models and the future of Physical AI with NVIDIA
WithMing-Yu Liu
49 minFrom AGENTS.md to Enterprise Deployment
WithNick Kuhn
1 h 01Questions people ask
- What is flow matching in AI image generation?
- Flow matching is a newer technique in AI image generation that Dustin Podell explains as an evolution from diffusion models, contributing to more powerful visual intelligence.
- What are the FLUX models?
- The FLUX family of models are discussed as part of the advancements in image generation, with a specific mention of FLUX.1 for in-context image generation and editing.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Daniel Whitenack and Chris Benson.