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("un-43/softserve_anime")
prompt = "a smart person, sftsrv style"
image = pipe(prompt).images[0]SoftServe Anime
- Prompt
- a smart person, sftsrv style
- Prompt
- a girl wearing a duck themed raincaot, sftsrv style
.png)
- Prompt
- a cup of yogurt, sftsrv style
.png)
- Prompt
- a stack of pancakes with fruit between the layers and whipped cream on top on a pastel green plate, sftsrv style
.png)
- Prompt
- a woman in smoke
- Prompt
- a cat in a field of purple flowers
- Prompt
- a hippie man walking through a field
Model description
This is a newly trained Flux Dev model, Dim/Rank 64 so it is a bit larger. Still working out the quirks!
This model is Sponsored by Glif! I wouldn't be able to access what I need and train / retrain so many Flux models without their support! ( http://glif.app )
Trigger words
You should use sftsrv style illustration 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
- 6
Model tree for un-43/softserve_anime
Base model
black-forest-labs/FLUX.1-dev