import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("yonggao/flux-lora-anime-runner")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Flux LoRA - Anime Runner Style
A LoRA adapter for FLUX.1-schnell that generates anime-style illustrations of runners and athletes.
Model Details
- Base Model: black-forest-labs/FLUX.1-schnell
- Training Steps: 1500
- Trigger Word: animestyle
- Resolution: 512x512, 768x768, 1024x1024
- Training Images: 10 custom generated images
Usage
Include the trigger word animestyle in your prompts.
Example Prompts
- animestyle illustration of a runner, japanese anime art, cel-shaded coloring, large expressive eyes
- animestyle marathon athlete, anime aesthetic, dynamic running pose, speed lines
- animestyle jogger character, cute anime style, morning run scene, soft lighting
Training Details
Trained using ai-toolkit with:
- Optimizer: AdamW 8bit
- Learning rate: 1e-4
- Batch size: 1
- Gradient accumulation: 4
- EMA decay: 0.99
License
Apache 2.0
- Downloads last month
- 9
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for yonggao/flux-lora-anime-runner
Base model
black-forest-labs/FLUX.1-schnell