How to use renderartist/toyboxflux with Diffusers:
pip install -U diffusers transformers accelerate
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("renderartist/toyboxflux") prompt = "t0yb0x 3d render of a toy design, a rocket" image = pipe(prompt).images[0]
First, this is super cool. To be able to combine AI images from other models and fine-tune another is pretty cool.
Second, do you have a guide on how to train the LoRAs?
Thanks!
· Sign up or log in to comment
