# AI & Parametric Negotiation 2.0 > Generative AI as a technology is typically seen as a command-and-follow relationship. We rarely find a middle ground where the designer can employ the statistical probability of AI, and the AI can draw from the designer’s experience. This workshop continues our exploration… ## At a glance - Format: On-demand course - Price: €85.00 (list €100.00) - Difficulty: Beginner - Duration: 8 Hours - Schedule: Jan 3-4, 2026 - Instructors: Kedar Undale - Categories: Architectural Design, Artificial Intelligence, 3D Modeling, Visualization - Software: ComfyUI, Rhinoceros 3D, Grasshopper 3D, Flux, Nano Banana, Kling AI - Students: 45 - Rating: 5.0 / 5 - Canonical: https://paacademy.com/course/ai-parametric-negotiation-2-0 - Enroll: https://paacademy.com/course/ai-parametric-negotiation-2-0 --- ## About this course AI & Parametric Negotiation 2.0 is a course that teaches designers to merge parametric design with generative AI, transforming Grasshopper animations into site-integrated architectural visuals. Building on Part 1's pedagogy, students convert abstract pattern videos into architectural renders inside ComfyUI using Flux, ControlNet, and IPAdapter, then upscale and composite selected frames onto real sites with Nano Banana before assembling a final video with Kling AI and Adobe Premiere Pro. The course is Beginner level and expects basic familiarity with Rhino3D, with no prior ComfyUI experience required. ## What you'll learn - Explore how designers can create hybrid workflows with AI. - Critically think about how much AI influence we want in our designs by controlling the inputs. - Create a negotiable space between parametric design processes and AI tools. - Learn the language and workflows that AI understands, and identify where its limitations arise. - Understand how small changes in the workflow can drastically alter the output. - Develop workflows connecting parametric modeling to site integration with AI. - Build an iterative design mindset, redefining the role of architects and designers in the AI landscape. ## Methodology This workshop is designed for participants who are new to ComfyUI but have a basic understanding of Rhino3D. We will begin by exploring different generative AI models to identify which ones best suit our workflow. Newer models often produce higher-quality results but take longer to generate, while older models are faster but may compromise on quality. Participants will then create short animation sequences in Grasshopper and convert them into architectural spaces using AI models such as Flux, SDXL, and Gemini 2.5 inside ComfyUI. Throughout the process, we will use concepts like upscaling, ControlNet, IPAdapter, and image refinement. Finally, selected frames will be morphed onto real sites chosen by the participants. By the end of the workshop, participants will have developed an iterative workflow that connects parametric logic, generative AI interpretation, and contextual design visualization. The workshop aims to move beyond standalone generative AI tools and integrate them directly into design processes such as parametric modeling. Participants will use Grasshopper3D to create parametric animations, ComfyUI to convert those animations into architectural spaces placed on real sites, and Premiere Pro to combine them into cohesive video sequences. This workshop aims to move beyond standalone generative AI tools and integrate them directly into design processes such as parametric modeling. Participants will use Grasshopper3D to create parametric animations, ComfyUI to convert those animations into architectural spaces placed on real sites, and Premiere Pro to combine them into cohesive video sequences. Stage 1 | Parametric Animations Participants will learn key Grasshopper3D concepts like data trees, color coding, and wire connections, and explore how to animate frames using sliders and different plugins. In this stage, we will be working with abstract patterns, but participants can choose their own designs as well. The focus is on building an understanding of animation within the Grasshopper interface. Stage 2 | Animation to ComfyUI Render This stage introduces core AI concepts such as checkpoint models, VAEs, and prompts before translating Grasshopper frames into architectural renders using ComfyUI. Participants will use ControlNet models (Depth and Sketch) and IPAdapter to guide and style their outputs. Stage 3 | Render to Site Participants will select preferred designs and integrate them onto real sites using upscaling with SDXL and FLUX, followed by compositing through Gemini 2.5 Flash Preview. Image editing will refine lighting, weather, and time of day for contextual realism. Stage 4 | Combining in Adobe Premiere Pro Participants will bring their sequences together in Premiere Pro, learning basic editing, keyframing, adding text, and making video adjustments to create smooth animations. ### Program: ### Day 1 – Parametric Animation to Rough Architectural Space Tools: Rhino3D, Grasshopper3D (Plugin – Heteroptera), ComfyUI (SDXL Turbo, SDXL Depth + Sketch ControlNet, IPAdapter), Adobe Premiere Pro Generating Parametric Animation from Grasshopper - Introduction to data trees, color coding, sliders, and wire connections - Adjusting camera location for better output - Extracting animation frames Animated Frames to Architectural Space - Retaining the design language of animation using ControlNet - Transferring style from an existing image with IPAdapter Combining Frames into Video in Adobe Premiere Pro - Introduction to the Premiere Pro interface, importing stills, and learning key frames - Adjusting motion properties to get a smooth animation - Assignment 1 + Q&A - Outcome: Final video output ### Day 2 – Site Implementation of the Design Tools: ComfyUI (Flux.1 Dev, Gemini 2.5 Flash Image (Nano Banana), Flux Kontext Max), Adobe Premiere Pro, Kling or WAN 2.2 Upscaling One Frame from Day 1 - Cropping the image - Comparing SDXL and FLUX upscaling methods - Exploring denoising and image refinement concepts Merging the Upscaled Design with the Site - Upscaling the site photograph - Morphing the generated design onto the site context Image Editing - Changing views, climate, or interior scene of the design Combining Everything - Video generation with Kling or WAN 2.2 - Combining in Adobe Premiere Pro - Assignment 2 + Q&A - Outcome: Final video and 3D model output ## Curriculum ### Session 1 - Introduction + PAACADEMY Updates (04:51) - AI Site Integration Workflow (17:34) - ComfyUI Basics (42:41) - ComfyUI Upscaling Workflow (34:47) - Site Image Refinement Guide (44:21) - Grasshopper Animation for AI (30:04) - Shrink Wrap Design Logic (33:06) ### Session 2 - AI Animation Design Workflow (11:06) - Advanced ControlNet Stacking (39:32) - Advanced Upscaling Strategies (57:57) - Advanced Site Integration Logic (51:29) - AI Video Compilation Workflow (48:17) ## FAQ ### What software and AI tools will I need for this workshop? You will use Rhinoceros 3D, Grasshopper 3D, ComfyUI (utilizing Flux, SDXL, Gemini 2.5/Nano Banana), Adobe Premiere Pro, and video AI models. ### What prior experience is recommended before joining this workshop? The course is beginner-friendly for ComfyUI, though participants are expected to have a basic understanding of Rhino 3D. ### How will parametric animations created in Grasshopper be converted into architectural renders? You will extract abstract animation frames from Grasshopper and use ComfyUI with ControlNet (Depth and Sketch) and IPAdapter to translate those frames into styled architectural spaces. ### What workflow will be taught to integrate generated architectural concepts onto real site photographs? You will learn to upscale generated designs using SDXL and FLUX, morph them onto real site contexts via Gemini 2.5 Flash Preview, and adjust contextual elements such as lighting, climate, and view angles. ### hat final deliverables will I create by the end of the workshop?] You will produce an iterative hybrid workflow output that includes upscaled architectural renders, site-integrated visual composites, a 3D model, and an edited video sequence assembled in Adobe Premiere Pro.