Do I need prior experience with ComfyUI or Flux models to attend?

No. The workshop starts with foundational workflows and progressively introduces more advanced tools, making it suitable for both beginners and experienced users exploring Flux

Will I be able to generate videos and 3D models by the end of the course?

On Day 2, the workshop covers Kling AI for generating videos from your images and Hunyuan 2.5 for converting images into 3D models, including a full walkthrough of both workflows.

Will I learn how to use different tools within the Flux model suite?

Yes. The workshop introduces each model in the Flux suite—covering everything from fast ideation to detailed refinements and image editing

Can I guide the style and mood of my architectural outputs?

Yes. You'll learn techniques to influence your visuals with specific styles, references, and design themes to better match your creative direction.

Is this workshop useful for professional architectural practice?

Yes. While the focus is on early-stage design and visualization, the skills you gain are highly applicable to concept development, client presentations, and design research.

Aug 30-31, 202513 lessonsIntermediate

FREE with Full Access Aug 30-31, 2025 Workshop Intermediate 13 lessons 5.0 Rating

The Diffusion Architect 3.0: Flux Era

Name: The Diffusion Architect 3.0: Flux Era
Price: 161.50 EUR
Availability: InStock
Rating: 5.00 (15 reviews)

The Diffusion Architect 3.0: Flux Era is a course that teaches architects to master the Flux model suite within ComfyUI, moving from fast text-to-image ideation to complex, multi-conditional workflows. Students apply Flux Schnell and Flux Dev with ControlNet, LoRAs, and Flux Redux for styled, controlled outputs, use Flux Fill for inpainting and upscaling, then combine these techniques with Flux Kontext Dev for multimodal image-and-text editing, Kling AI for image-to-video animation, and Hunyuan 2.5 to convert 2D images into 3D models. The course is Intermediate level and expects prior familiarity with ComfyUI.

This course includes

Live workshop · 7h 52m
Lifetime session recordings
Certificate of completion
Downloadable course files
4 design tools
Private Discord community
Included with Full Access
Aug 30-31, 2025

Step into the Flux Era where cutting-edge AI models are transforming the way we design and visualize architecture.

This two-day intensive workshop will focus on equipping architects, designers, and visual artists with the skills to fully harness the power of the Flux model suite within ComfyUI.

This workshop will teach you how to move from fast ideation to highly controlled, stylistically rich outputs creating architectural imagery that is not only visually stunning but also technically adaptable and deeply responsive to design intent.

Whether your goal is to generate mood boards, develop intricate facades, or build immersive environments, this workshop will teach you how to integrate advanced AI tools into your creative process for next-level architectural storytelling.

For detailed installation guides, please check the workshop’s Google Drive. To access it, click "Watch Now" → "Files" → "Download Course Files"

Generate architectural images using the full Flux model suite in ComfyUI.
Build fast text-to-image workflows with Flux Schnell.
Apply LoRAs and image references for custom styles.
Guide designs with ControlNets and refine using flux fill.
Combine tools into advanced, flexible workflows.
Edit images with text and visuals using Kontext Dev.
Create animated architectural videos with Kling AI.
Turn 2D images into 3D models using Hunyuan 2.5.

This workshop will provide architects with a comprehensive mastery of the Flux model suite, moving from foundational text-to-image to complex, multi-conditional workflows.

The workshop focuses on leveraging the unique capabilities of each Flux variant to achieve unparalleled control, quality, and efficiency in architectural concept generation, refinement, and translation into dynamic video and 3D forms.

Program:

Day 1: Flux Foundations & Core Architectural Techniques (4 Hours)

Focus: Building a deep understanding of the core Flux models and mastering the essential techniques for image generation, control, and refinement in an architectural context.

Hour 1: Introduction to the Flux Era & Core Generation

Presentation: The Diffusion Architect 3.0 – Why the Flux Era?

Overview of the Flux architecture: What makes it a paradigm shift from previous models (speed, efficiency, transformer base).
Introduction to the specific Flux variants and their roles:
- schnell (speed)
- dev (quality/control)
- fill (utility)
- kontext dev (multimodality)

Text-to-Image with flux schnell

Creating a foundational text-to-image workflow in ComfyUI.
Exploring the speed and characteristics of flux schnell for rapid architectural ideation and concept development.
Prompting strategies tailored to schnell's behavior.

Tool Focus: ComfyUI, flux schnell.

Hour 2: Image-to-Image & Foundational Control

Image-to-Image with flux schnell

Adapting the workflow for img2img tasks.
Understanding key parameters (denoise) for stylistic transfer and refinement.

Image-to-Image + ControlNets with flux dev

Introducing flux dev for higher-fidelity outputs.
Integrating ControlNets: Why flux dev is often preferred for controlled workflows.

Architectural Control Tools: flux canny + flux depth

Practical application of canny (from sketches/line drawings) and depth (from simple 3D massing) using flux dev workflows.

Tool Focus: ComfyUI, flux schnell, flux dev, ControlNet (canny, depth).

Hour 3: Advanced Direction & Stylistic Influence

Deep Dive into flux loras

Understanding how LoRAs are implemented and interact specifically with Flux models.
Sourcing, applying, and weighting architectural LoRAs for targeted stylistic control (e.g., Brutalism, Biophilic design, specific material palettes).

Image Referencing with flux redux (IPAdapter)

Mastering image-to-image referencing workflows for consistent style, mood, and compositional guidance.
Balancing prompt, LoRA, and redux influences.

Tool Focus: ComfyUI, flux dev, Flux-compatible LoRAs, flux redux (IPAdapter).

Hour 4: Essential Utilities & Image Finalization

Corrective Inpainting with flux fill

Introduction to flux fill for seamless inpainting and outpainting.
Architectural use cases: Refining details, removing unwanted artifacts, extending canvases, and targeted design modifications.

High-Resolution Upscaling with flux dev

Techniques for upscaling generated images for presentation while preserving detail and coherence, using workflows centered on flux dev.

Day 1 Wrap-up & Q&A

Review of the core Flux workflows and techniques covered.
Open Q&A session.

Day 2: Advanced Combinations, Multimodality & Dimensional Leaps (4 Hours)

Focus: Synergizing the learned techniques into complex workflows, exploring multimodal generation, and translating 2D masterpieces into dynamic video and 3D forms.

Hour 1: The Combinational Workflow – Total Control

Building the Ultimate Architectural Workflow

This hour is dedicated to constructing a complex, synergistic workflow from the ground up.
Layering multiple techniques for maximum creative control:
- flux dev as the base
- Conditioned by multiple ControlNets (flux canny, etc.)
- Guided by flux redux referencing
- Stylized by flux loras
Strategies for organizing and managing complex ComfyUI graphs.
Live demonstration: Creating a highly detailed and specific architectural scene using the full combinational workflow.

Tool Focus: All Day 1 tools combined.

Hour 2: Multimodal Generation with flux kontext dev

Exploring the Frontier: Multimodal Interaction

Deep dive into flux kontext dev: Understanding its unique ability to process both image and text prompts simultaneously for in-context editing and generation.

Demonstrating powerful use cases:

Style Transfer: "Make this photorealistic image look like an anime sketch."
Object/Subject Tweaks: "Change the building material from concrete to timber."
Text Editing: "Change the sign on the building to say 'Library'."
Comparing flux kontext dev to traditional inpainting and img2img methods.

Tool Focus: ComfyUI, flux kontext dev.

Hour 3: Image-to-Video with Kling AI

Bringing Architecture to Life

Taking high-quality images generated from the combinational or multimodal workflows and translating them into video.
Workflow and best practices for preparing images for Kling AI.
Exploring Kling's capabilities for creating dynamic camera movements, atmospheric effects, and short architectural fly-throughs.

Tool Focus: Kling AI; ComfyUI (for source image preparation).

Hour 4: The Final Dimension – Image-to-3D

Image-to-3D with Hunyuan 2.5

The final leap: Using refined 2D images as a source for 3D model generation.
Introduction to Hunyuan 2.5: Capabilities, ideal input characteristics, and workflow.
Step-by-step process of generating a 3D model from a selected architectural image.

Assessing & Integrating the 3D Output

Critical analysis of the generated 3D model's geometry, texture, and suitability for architectural conceptualization.
Brief overview of potential next steps (e.g., cleanup in Rhino/Blender).

Final Remarks & Future of Flux

Recap of the entire Flux ecosystem journey.
Discussion on the future trajectory of generative AI for architects.
Final Q&A session.

Tool Focus: Hunyuan 2.5

Ismail Seleit

Verified Account

4 Courses4.0

View profile

Ismail Seleit is a distinguished architect at Foster + Partners, renowned for his expertise in computational design and BIM (Building Information Modeling). His work encompasses various projects, from design competitions to complex building realizations. Ismail is dedicated to integrating advanced AI tools, such as Stable Diffusion and ControlNet, into architectural workflows, pushing the boundaries of design innovation. Beyond architecture, he is an accomplished ambient-electronic music producer, creating soundtracks for architectural films and various independent projects, showcasing his multifaceted creativity and technical skills.

Purchase or enroll in this course to leave a review.

5.0avg15 Reviews

15 Comments

Alexandre Guilbeault

Thanks

Jun 15, 2026

Dino Krizmanic

Very informative and helpfull even for someone who has some knowlege on the themes discussed

Mar 13, 2026

Gregor Hilpert

Short Update for Flux 2?

Feb 13, 2026

Kaloyan Valkanov

Good overview of the flux models and impact of LoRAs. Would be great if there is a separate workshop solely focused on trainig LoRAs.

Jan 12, 2026

Marcella Carone

Amazing workshop

Jan 6, 2026

Dunja Predic

Very practical workshop !

Jan 2, 2026

Chiemeka Ejiochi

excellent course

Dec 29, 2025

Thomas Nelissen

Super good course

Nov 22, 2025

Abdallah Manzalawi

Great WORKSHOP

Oct 11, 2025

Jaime Andrade

Nice course.

Oct 10, 2025

Jose Andres

Great course! insightful and practical

Oct 4, 2025

Oleg Kauz

nice tutors and workshops! but a little bit difficult website to get certificate...

Sep 2, 2025

Pressouyre Jonathan

amazing course, Ismail is a great instructor

Sep 2, 2025

Anas Qudsi

The course was amazing, as a first timer in comfyUI and all these tools I found the way Ismail explained was very easy to understand and I was able to follow up with everything he has done. I will be watching everything twice maybe more to fully grasp everything but in general was mind blowing! Thanks a lot!!

Aug 31, 2025

Dana Tulaimat

Very informative session with Ismail, a great lecturer, liked how packed the sessions were, it was relatively easy to follow, although I think it needs to be clarified that attendees need to be familiar with comfyUI.