Flux LoRAs
Collection
7 items β’ Updated β’ 3
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("bingbangboom/flux_whimscape")
prompt = "a girl wearing glasses, wearing a baseball cap, holding a boba tea cup with a straw in her hand, illustration in the style of WHMSCPE001"
image = pipe(prompt).images[0]








![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
Flux LoRA for creating whimsical illustrations. Use 'illustration in the style of WHMSCPE001' to trigger the model. Best with DEV (works well even with fp8). To use with flux1-dev-bnb-nf4 try increasing the LoRA strength (say 1.3 and then adjust accordingly)
You should use illustration in the style of WHMSCPE001 to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Trained at Replicate using: https://replicate.com/ostris/flux-dev-lora-trainer/train
Base model
black-forest-labs/FLUX.1-dev