Downloads · 30 days
36
1% of all-time downloads
ludocomito/flux-lora-kuji
flux-lora-kuji is a text-to-image model from ludocomito. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as other.
Downloads · 30 days
36
1% of all-time downloads
All-time downloads
3.3K
Public
Repo size
172 MB
Likes
11
Public
Click a slice to open those files.
.safetensors172 MB · 99%
From the Hugging Face model README
A Huji cam inspired lora finetuning of flux-koda. Works best with landscapes and naturalistic environments. In order to obtain better results, combine the keywords 'flmft' and 'in the style of KUJI'. More examples in this drive folder.
Fun fact: training set was mostly made by images taken by me 🤗.
Trained on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
Combine the keywords 'flmft' and 'in the style of KUJI'
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('ludocomito/flux-lora-kuji', weight_name='lora.safetensors')
image = pipeline('your prompt').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers