Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is not available for use and might generate different characters compared to the ones seen in the images.

Model Description by Creator

A light fun project - trained a model on 3d holographic-looking assets. It will give objects iridescent colors and a shiny surface. 

Trained on 33 images of mostly abstract shapes and objects. Turns out it’s quite challenging to describe abstract-looking objects using words (e.g. “a pink and blue blob”). Base SD’s knowledge in some cases can also be limited - things like “raindrop”, “blob” or “sphere” will work, but “tetrahedron” or “figure 8” will not. As a result of these two factors, prompting can be a bit tricky (will sometimes result in random 3d shapes) and requires patience.

Join our Discord for any questions or feedback!

Prompting

Describe the object you want, along if the colors if desired.

Example prompts

  • A pink and blue donut 

  • A black wavy sheet of paper

  • Waves on the ocean

The training images were mostly abstract objects along with a few common shapes, so the model will perform the best on these. 

Settings

Resolution is 512 x 512. 

Sample images were using CFG = 11 and 75 inference steps.

Images Generated With This Model

flowing water
flowing water
a pink and blue donut
a pink and blue donut
neon
neon
neon
neon
a teardrop
a teardrop
magma
magma
a black wavy sheet of paper
a black wavy sheet of paper
a sphere
a sphere
a rainbow spiral
a rainbow spiral
a sea urchin
a sea urchin
(detailed:1.1), datacenter, servers hallway, computers, hyperrealistic, neon lighting, (best quality:1.1), <lora:datacenters-lora-v0.1:0.9>, liminal space
(detailed:1.1), datacenter, servers hallway, computers, hyperrealistic, neon lighting, (best quality:1.1), <lora:datacenters-lora-v0.1:0.9>, liminal space
(detailed:1.1), datacenter, servers hallway, computers, hyperrealistic, neon lighting, (best quality:1.1), <lora:datacenters-lora-v0.1:0.9>, liminal space
(detailed:1.1), datacenter, servers hallway, computers, hyperrealistic, neon lighting, (best quality:1.1), <lora:datacenters-lora-v0.1:0.9>, liminal space

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.