import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("iamkaikai/amazing-logos-lora")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]This pipeline uses a LoRA model that has been finetuned from the runwayml/stable-diffusion-v1-5 base model on the iamkaikai/amazing_logos dataset with Nvidia A6000.
- train_batch_size=14
- gradient_accumulation_steps=30
- max_train_steps=3000
- learning_rate=1e-04
- lr_scheduler="cosine" --lr_warmup_steps=2900
Prompt Format
The prompt format is as follows:
{template keywords} + [company name] + [concept & country] + {template keywords}
For example:
Simple elegant logo for a **[Google]**, **[G circle United states]**, successful vibe, minimalist, thought-provoking, abstract, recognizable
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
Here are some examples of prompts:
- Simple elegant logo for a Digital Art, D A circle, successful vibe, minimalist, thought-provoking, abstract, recognizable
- Simple elegant logo for a 3M Technology Products, 3 M triangles square United states, successful vibe, minimalist, thought-provoking, abstract, recognizable
- Simple elegant logo for a 38Energy, lines drop fire flame water, successful vibe, minimalist, thought provoking, abstract, recognizable, relatable, sharp, vector art, even edges
Preview
- Downloads last month
- 3
Model tree for iamkaikai/amazing-logos-lora
Base model
runwayml/stable-diffusion-v1-5