Product Design (minimalism-eddiemauro) LORA

Hi, I’m a product and car designer, and I’m so excited to test with AI, I think is a good tool for designing. This tool is so useful for the design process (shapes-ideas generation), but more than that it helps so much to refine aesthetically. I created a basic Lora and tested it with so many kinds of checkpoints, and the result was a different type of “minimalism”.

ORIGINAL MODEL: eddiemauro 1.5 (Checkpoint). Express the minimalism concept. Matte finishing.

MINIMALIST (Lora): It is recommended to use like a checkpoint called “Deliberate” (but you can try with others), so download it first and load inside SD UI (example: Automatic1111):

https://civitai.com/models/4823/deliberate

The style is a bit darker with more contrast (taken from Deliberate), and preserves the minimalism style. The training dataset is the same as eddiemauro1.5 checkpoint and officially is the Lora General model for my checkpoint. After a lot of training and testing images, I finally arrived at a stable Lora model to generate product design images and iterations. Recommendation to use this model:

It is mandatory to use captions in the prompt: “emauromin style”.
Clip Skip 2. Go to settings-Stable Diffusion-Clip Skip, and put “2”. I trained model with this option.
Generate first some images by changing “Batch size”, select one, and go to img2img mode, duplicate or increase resolution (image size), with “denoise strength” of “0.3 to 0.5”. It is the same process of “hires.fix” in txt2img mode, but you can have more images generated to select. Try to preserve 512×512 (or just 512 on one side) because images are trained at this resolution, and when you change it the model-shapes start gets crazy, even that you can experiment.
Use new “extra tool” for enhancing image called “4x-UltraSharp”, to increase final resolution.
Try to use lora level from 0.8 to 1 in the prompt.
Use ControlNet to generate a more controlled shape of what you want, and even you can test it with sketches. Some images shown here were created with projects that I have done, if you like, you can take like a base one of my creations: https://www.behance.net/eadesign1
You can use this model for whatever you want. If there is another app that is using my model, and you have to pay for it, just let me know. If you use it for merge, I would just ask to contact me.
You can download “EasyNegative” embedding and use it.
Use VAE 560000 or 840000 of SD model 1.5, to enhance the image created. Sometimes works.

The sample images here were created with my model, and it has not any inpainting or post-production, just were upscaled with A111 models. You have to consider that you have to experiment so much to arrive at these results because it is hard to test just once and get an ideal result. I use Automatic1111 with most used extensions.

I trained this model with 100 images with a “minimalistic” style (probably I will train more styles). 75% were products and 22% transportation, from that most of these are speakers, smart robots, water bottles, and others. I will enhance the models by adding 100 more images with a variety of shapes and different types. I realized that these models work so well in vehicle-car shapes, even that if were not so many vehicles in the training dataset.

Example Prompt:

Positive prompt: emauromin style, futuristic armchair, finely detailed, purism, ue 5, a computer rendering, minimalism, octane render, 4k <lora:eddiemauroLora2:0.8>

Negative prompt: (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, bad_prompt, bad_prompt2, ((monochrome)), ((grayscale)), cropped, text, jpeg artifacts, signature, watermark, username, EasyNegative,sketch, cartoon, drawing, anime, duplicate, blurry, semi-realistic, out of frame, worst quality, ugly, low quality, deformed, multiple objects