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("CalvinHerbst/Synthesia")
prompt = "-"
image = pipe(prompt).images[0]Synthesia
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
Model description
Synthesia recommended settings:
Strength: 2.0 (up to 4.0 for extreme degradation, down to 0.5 for subtle effects)
Flux Guidance: 2.5 (higher for anime)
Max shift: 0
Base shift: 8
Schedulers and samplers produce a variety of aesthetics.
This is a distilled model.
Trigger words
You should use synthesia 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
- 1
Model tree for CalvinHerbst/Synthesia
Base model
black-forest-labs/FLUX.1-dev