metadata
license: other
license_name: flux1dev
tags:
- text-to-image
- diffusers
- lora
- flux
- flux-diffusers
- template:sd-lora
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Paper Cutout Style
widget:
- text: >-
1980s anime screengrab, VHS quality, a woman with her face glitching and
disorted, a halo above her head
output:
url: assets/angel.png
- text: >-
Still frame from a 1980s vintage manga, cell shaded, a wall made of eyes,
VHS quality,
output:
url: assets/eyes.png
- text: >-
Still frame from a 1980s vintage manga, cell shaded, where a girl is
holding a lantern to a wall made out of faces, VHS quality,
output:
url: assets/wall.png
- text: >-
Still frame from a 1980s vintage manga where an anime couple dip their
toes in a galaxy lake, nature, VHS quality
output:
url: assets/galaxy.png
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
- Prompt
- 1980s anime screengrab, VHS quality, a woman with her face glitching and disorted, a halo above her head
- Prompt
- Still frame from a 1980s vintage manga, cell shaded, a wall made of eyes, VHS quality,
- Prompt
- Still frame from a 1980s vintage manga, cell shaded, where a girl is holding a lantern to a wall made out of faces, VHS quality,
- Prompt
- Still frame from a 1980s vintage manga where an anime couple dip their toes in a galaxy lake, nature, VHS quality
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.