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("AlekseyCalvin/Portra800")
prompt = "TOK style"
image = pipe(prompt).images[0]Kodak Portra 800-inspired Realistic Model by Shapestudio (Fine-tuned from Flux Schnell/Dev)
Model description
Also found/usable via Replicate HERE
Trigger words
You should use 'TOK style' to trigger the image generation.
- Downloads last month
- 22
Model tree for AlekseyCalvin/Portra800
Base model
black-forest-labs/FLUX.1-dev