AI Images, LLM, ChatGPT

During the Varese RetroComputing 2024, a fair increasingly rich in not only vintage but also current content, I had the pleasure of interviewing Michele Petino, who professionally deals with 3D modeling, rendering, virtual tours and lessons on the implementation of AI in the production of images and renders. It was a meeting full of technical ideas, where we talked about both AI images and the world of three-dimensional modeling, passing through advanced tools such as ComfyUI, FLUX.1 [dev], Civitai, Stable Diffusion, ChatGPT, SketchUp and D5 Render.

Generative AI: experimentation and creative flow for AI images

Michele Petino uses generative artificial intelligence to create images and visual experiences with a high level of control. The basis of its flow is a well-organized ecosystem of software and resources, which rely on high-performance hardware: Intel Core i9 and NVIDIA GeForce RTX 4090.

ComfyUI: the modular interface for Stable Diffusion

Among the most interesting tools presented by Michele is ComfyUI, a visual interface with nodes that allows you to control in detail all the phases of rendering with Stable Diffusion. ComfyUI allows the construction of customized and complex flows, suitable for those who want full mastery of the creative process. Each node represents a distinct operation (prompts, templates, initial images, filters, transformations) and the system allows real-time visual testing.

Civitai: community, custom models and sharing

As for the choice of models, Michele refers to Civitai, an online platform where it is possible to download and upload customized models for Stable Diffusion. Here you will find models trained on specific datasets, suitable for particular styles, characters, settings and even real photographs. This asset easily integrates with ComfyUI, offering a wide range of creative possibilities.

The model used by Michele Petino in the interview is by the user Tenofas of Civitai.

FLUX.1 [dev] and LLM Prompt Generator: Creative Control Over Prompts

Another tool mentioned by Michele is FLUX.1 [dev]. It is an interface oriented towards image generation via AI, but strongly integrated with the language capabilities of LLMs. In particular, FLUX.1 interfaces with models such as ChatGPT, exploiting its semantic capabilities to generate optimized text prompts. Combined with the LLM Prompt Generator, FLUX allows you to refine, vary and expand prompts through guided interaction, drastically improving the quality of the images produced.

LLM and ChatGPT: intelligent assistants in the AI image creative process

Another central point of the interview is the use of ChatGPT and LLMs (Large Language Models) as real creative assistants. Michele tells us how, through textual interaction, these models are able to generate descriptive prompts for the creation of AI images.

Photorealistic 3D Modeling and Rendering: SketchUp and D5 Render

In the second part of the interview, Michele takes us into his professional field: the creation of 3D animations and architectural renderings. Artificial intelligence is less present here, but the technical level remains high.

To model the environments, Michele uses SketchUp, one of the most popular software for 3D design in the architectural field. With SketchUp, he builds volumes, structures and furnishings, while maintaining a high level of precision and compatibility.

The final rendering is done via D5 Render, a real-time rendering engine that combines visual quality and speed. D5 Render also uses some AI technologies for the processing of lights, shadows and materials, generating photorealistic results in a much shorter time than traditional software.

Thanks to D5 Render, Michele is able to produce animations, walkthroughs and images of the highest quality, often used in promotional or architectural fields.

During the interview, Michele showed us an animation of an airplane.

Subscribe to my channel and stay up to date

To stay up to date on topics related to computers and vintage electronics, but also more modern, I invite you to subscribe to the YouTube channel @ValorosoIT and activate the notification bell so you don't miss the next videos. I'm also present on TikTok, Instagram, Facebook, Threads ...

Do you like this page? Share it: