Mark Theriault based the startup FITY envisioning a line of intelligent cooling merchandise: chilly drink holders that include freezable pucks to maintain drinks chilly for longer with out the mess of ice. The entrepreneur began with 3D prints of merchandise in his basement, constructing one unit at a time, earlier than ultimately scaling to mass manufacturing.
Founding a client product firm from scratch was a tall order for a single particular person. Going from preliminary sketches to production-ready designs was a significant problem. To convey his inventive imaginative and prescient to life, Theriault relied on AI and his NVIDIA GeForce RTX-equipped system. For him, AI isn’t only a software — it’s a complete pipeline to assist him accomplish his targets. Learn extra about his workflow under.
Plus, GeForce RTX 5050 laptops begin arriving right now at retailers worldwide, from $999. GeForce RTX 5050 Laptop computer GPUs function 2,560 NVIDIA Blackwell CUDA cores, fifth-generation AI Tensor Cores, fourth-generation RT Cores, a ninth-generation NVENC encoder and a sixth-generation NVDEC decoder.
As well as, NVIDIA’s Plug and Play: Venture G-Help Plug-In Hackathon — working nearly via Wednesday, July 16 — invitations builders to discover AI and construct customized G-Help plug-ins for an opportunity to win prizes. Save the date for the G-Help Plug-In webinar on Wednesday, July 9, from 10-11 a.m. PT, to study extra about Venture G-Help capabilities and fundamentals, and to take part in a stay Q&A session.
From Idea to Completion
To create his standout merchandise, Theriault tinkers with potential FITY Flex cooler designs with conventional strategies, from sketch to computer-aided design to speedy prototyping, till he finds the precise imaginative and prescient. A novel side of the FITY Flex design is that it may be custom-made with enjoyable, common shoe charms.
For packaging design inspiration, Theriault makes use of his most popular text-to-image generative AI mannequin for prototyping, Steady Diffusion XL — which runs 60% sooner with the NVIDIA TensorRT software program growth package — utilizing the modular, node-based interface ComfyUI.
ComfyUI provides customers granular management over each step of the technology course of — prompting, sampling, mannequin loading, picture conditioning and post-processing. It’s ideally suited for superior customers like Theriault who wish to customise how photos are generated.
NVIDIA and GeForce RTX GPUs primarily based on the NVIDIA Blackwell structure embrace fifth-generation Tensor Cores designed to speed up AI and deep studying workloads. These GPUs work with CUDA optimizations in PyTorch to seamlessly speed up ComfyUI, decreasing technology time on FLUX.1-dev, a picture technology mannequin from Black Forest Labs, from two minutes per picture on the Mac M3 Extremely to about 4 seconds on the GeForce RTX 5090 desktop GPU.
ComfyUI can even add ControlNets — AI fashions that assist management picture technology — that Theriault makes use of for duties like guiding human poses, setting compositions by way of depth mapping and changing scribbles to pictures.
Theriault even creates his personal fine-tuned fashions to maintain his type constant. He used low-rank adaptation (LoRA) fashions — small, environment friendly adapters into particular layers of the community — enabling hyper-customized technology with minimal compute price.
“Over the previous couple of months, I’ve been shifting from AI-assisted pc graphics renders to totally AI-generated product imagery utilizing a customized Flux LoRA I skilled in home. My RTX 4080 SUPER GPU has been important for getting the efficiency I want to coach and iterate rapidly.” – Mark Theriault, founding father of FITY
Theriault additionally faucets into generative AI to create advertising belongings like FITY Flex product packaging. He makes use of FLUX.1, which excels at producing legible textual content inside photos, addressing a typical problem in text-to-image fashions.
Although FLUX.1 fashions can sometimes devour over 23GB of VRAM, NVIDIA has collaborated with Black Forest Labs to assist cut back the scale of those fashions utilizing quantization — a way that reduces mannequin dimension whereas sustaining high quality. The fashions have been then accelerated with TensorRT, which supplies an as much as 2x speedup over PyTorch.
To simplify utilizing these fashions in ComfyUI, NVIDIA created the FLUX.1 NIM microservice, a containerized model of FLUX.1 that may be loaded in ComfyUI and permits FP4 quantization and TensorRT help. Mixed, the fashions come down to simply over 11GB of VRAM, and efficiency improves by 2.5x.
Theriault makes use of the Blender Cycles app to render out ultimate recordsdata. For 3D workflows, NVIDIA affords the AI Blueprint for 3D-guided generative AI to ease the positioning and composition of 3D photos, so anybody on this technique can rapidly get began.
Lastly, Theriault makes use of giant language fashions to generate advertising copy — tailor-made for SEO, tone and storytelling — in addition to to finish his patent and provisional purposes, work that normally prices 1000’s of {dollars} in authorized charges and appreciable time.
“As a one-man band with a ton of content material to generate, having on-the-fly technology capabilities for my product designs actually helps pace issues up.” – Mark Theriault, founding father of FITY
Each texture, each phrase, each photograph, each accent was a micro-decision, Theriault mentioned. AI helped him survive the “loss of life by a thousand cuts” that may stall solo startup founders, he added.
Every week, the RTX AI Storage weblog collection options community-driven AI improvements and content material for these seeking to study extra about NVIDIA NIM microservices and AI Blueprints, in addition to constructing AI brokers, inventive workflows, digital people, productiveness apps and extra on AI PCs and workstations.
Plug in to NVIDIA AI PC on Fb, Instagram, TikTok and X — and keep knowledgeable by subscribing to the RTX AI PC e-newsletter.
Observe NVIDIA Workstation on LinkedIn and X.
See discover relating to software program product info.