metadata
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
instance_prompt: JO
widget:
- text: >-
Jo, a 41-year-old father, smiling as he looks out the window and sees
planet Earth, in a spaceship, wearing an astronaut orange suit with the
NASA symbol. He is looking forward to returning to his family. The ship is
entering the atmosphere and there is a reflection of intense light coming
through the window. Breathtaking, cinematic, exciting, harmonious, highly
detailed, high budget, bokeh, cinemascope, atmospheric, epic, stunning,
UHD 8K, 85mm, Fujifilm GFX100 II, soft light, warm composition,
output:
url: images/example_o3cc76dfs.png
Jo Flux
- Prompt
- Jo, a 41-year-old father, smiling as he looks out the window and sees planet Earth, in a spaceship, wearing an astronaut orange suit with the NASA symbol. He is looking forward to returning to his family. The ship is entering the atmosphere and there is a reflection of intense light coming through the window. Breathtaking, cinematic, exciting, harmonious, highly detailed, high budget, bokeh, cinemascope, atmospheric, epic, stunning, UHD 8K, 85mm, Fujifilm GFX100 II, soft light, warm composition,
Trained on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
Trigger words
You should use JO to trigger the image generation.
Use it with the 🧨 diffusers library
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('jmxt/jo-flux', 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