Downloads · 30 days
168
0% of all-time downloads
adirik/flux-cinestill
flux-cinestill is a text-to-image model from adirik. 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
168
0% of all-time downloads
All-time downloads
146K
Public
Repo size
861 MB
Likes
53
Public
Click a slice to open those files.
.safetensors172 MB · 98%
From the Hugging Face model README
FLUX.1-Dev LoRA fine tuned on Cinestill 800T images on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
Best suited for generating night and dusk time photograph-like images with a distinctive slight halation effect. Keywords that result in better generations "cinestill 800t", "night time", "dusk", "4k", "high resolution", "analog film".
You should use CNSTLL to trigger the image generation.
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('adirik/flux-cinestill', 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