import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Finanahnahnah/street_art")
prompt = "street_art, the image is a mixed-media artwork that appears to be a colorful and abstract composition, crowned raccoon playing with guitar"
image = pipe(prompt).images[0]Street Art
- Prompt
- street_art, the image is a mixed-media artwork that appears to be a colorful and abstract composition, crowned raccoon playing with guitar
- Prompt
- street_art, the image is a mixed-media artwork that appears to be a colorful and abstract composition, swimming pool
- Prompt
- street_art, the image is a mixed-media artwork that appears to be a colorful and abstract composition, skull and lilies in the universe
- Prompt
- street_art, the image is a mixed-media artwork that appears to be a colorful and abstract composition, steve jobs
Model description
A street art poster style.
I trained this LoRA using the AI toolkit(https://github.com/ostris/ai-toolkit). The configuration file used during training is here(https://huggingface.co/Finanahnahnah/street_art/blob/main/street_art.yaml), and the samples for monitoring training progress are here(https://huggingface.co/Finanahnahnah/street_art/blob/main/train_samples.jpg). The model achieved promising results by the 2400th training step.
Trigger words
You should use `street_art, the image is a mixed-media artwork that appears to be a colorful and abstract composition` to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 25
Model tree for Finanahnahnah/street_art
Base model
black-forest-labs/FLUX.1-dev