Model description
Lora trained on the unique style and prompting AI generated image aesthetic of r/SyntheticAnime. over 300 images were used to train this lora for 15 epochs.
32 rank lora
Trigger words
You should use 1980s anime screengrab, VHS quality,
or syntheticanime
to trigger the image generation.
Use it with the :firecracker: diffusers library
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('dataautogpt3/FLUX-SyntheticAnime', weight_name='Flux_1_Dev_LoRA_syntheticanime.safetensors')
image = pipeline('1980s anime screengrab, VHS quality, a woman with her face glitching and disorted, a halo above her head').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers
License
Please adhere to the licensing terms as described here.
- Downloads last month
- 3,796
Model tree for dataautogpt3/FLUX-SyntheticAnime
Base model
black-forest-labs/FLUX.1-dev