metadata
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
datasets:
- iamkaikai/amazing_logos_v3
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
Text-to-image finetuning - iamkaikai/amazing-logos
This pipeline was finetuned from runwayml/stable-diffusion-v1-5 on the iamkaikai/amazing_logos_v3 dataset.
Latest Update: v3 model expands the training dataset to 200k imgages.
Training info
These are the key hyperparameters used during training:
- Dataset size: 200k
- Epochs: 7
- Learning rate: 5e-07
- Batch size: 1
- Gradient accumulation steps: 2
- Image resolution: 512
- Mixed-precision: fp16
Prompt Format
The prompt format is as follows:
{template keywords} + [company name] + [concept & country] + [industry] + {template keywords}
For example:
Colored logo
Simple elegant logo for Google, G circle United states, technology, successful vibe, minimalist, thought-provoking, abstract, recognizable
monochrome logo (include "black and white")
Simple elegant logo for Google, G circle United states, technology, successful vibe, minimalist, thought-provoking, abstract, recognizable, black and white
Here are some examples of prompts:
- Simple elegant logo for Digital Art, D A square, education, successful vibe, minimalist, thought-provoking, abstract, recognizable
- Simple elegant logo for 3M Technology, 3 M square United states, technology and product, successful vibe, minimalist, thought-provoking, abstract, recognizable
- Simple elegant logo for 42Studio, lines drop fire flame water, design studio, successful vibe, minimalist, thought provoking, abstract, recognizable, relatable, sharp, vector art, even edges
The [concept & country] section can include words such as:
- lines
- circles
- triangles
- dot
- crosses
- waves
- square
- letters (A-Z)
- 3D
- Angled
- Arrows
- cube
- Diamond
- Hexagon
- Loops
- outline
- ovals
- rectangle
- reflection
- rings
- round
- semicircle
- spiral
- woven
- stars