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-v2
This pipeline was finetuned from runwayml/stable-diffusion-v1-5 on the iamkaikai/amazing_logos_v3 dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['Simple elegant logo for Digital Art, D A square terminal tech, successful vibe, minimalist, thought-provoking, abstract, recognizable, black and white', 'Simple elegant logo for Digital Art, D A arrow terminal tech, successful vibe, minimalist, thought-provoking, abstract, recognizable, black and white', 'Simple elegant logo for Digital Art, D A dots terminal tech, successful vibe, minimalist, thought-provoking, abstract, recognizable, black and white', 'Simple elegant logo for Digital Art, D A portal terminal tech, successful vibe, minimalist, thought-provoking, abstract, recognizable, black and white', 'Simple elegant logo for Digital Art, D A tech terminal tech, successful vibe, minimalist, thought-provoking, abstract, recognizable', 'Simple elegant logo for Digital Art, D A programming terminal tech, successful vibe, minimalist, thought-provoking, abstract, recognizable', 'Simple elegant logo for Digital Art, D A art terminal tech, successful vibe, minimalist, thought-provoking, abstract, recognizable', 'Simple elegant logo for Digital Art, D A digital terminal tech, successful vibe, minimalist, thought-provoking, abstract, recognizable', 'Simple elegant logo for DA, > A terminal tech, successful vibe, minimalist, thought-provoking, abstract, recognizable, black and white', 'Simple elegant logo for DA, D A portal art, successful vibe, minimalist, thought-provoking, abstract, recognizable, black and white', 'Simple elegant logo for DA, art tech school, successful vibe, minimalist, thought-provoking, abstract, recognizable, black and white', 'Simple elegant logo for DA, art tech school, successful vibe, minimalist, thought-provoking, abstract, recognizable', 'Simple elegant logo for DA, art tech school digital, successful vibe, minimalist, thought-provoking, abstract, recognizable', 'Simple elegant logo for DA, art tech school digital, successful vibe, minimalist, thought-provoking, abstract, recognizable, black and white', 'Simple elegant logo for DA, D A art tech, successful vibe, minimalist, thought-provoking, abstract, recognizable', 'Simple elegant logo for DA, D A digital art school, successful vibe, minimalist, thought-provoking, abstract, recognizable']:
Pipeline usage
You can use the pipeline like so:
from diffusers import DiffusionPipeline
import torch
pipeline = DiffusionPipeline.from_pretrained("iamkaikai/amazing-logos-v2", torch_dtype=torch.float16)
prompt = "Simple elegant logo for Digital Art, D A square terminal tech, successful vibe, minimalist, thought-provoking, abstract, recognizable, black and white"
image = pipeline(prompt).images[0]
image.save("my_image.png")
Training info
These are the key hyperparameters used during training:
- Epochs: 1
- Learning rate: 1e-07
- Batch size: 1
- Gradient accumulation steps: 1
- Image resolution: 512
- Mixed-precision: fp16
More information on all the CLI arguments and the environment are available on your wandb run page.