metadata
tags:
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
- ai-toolkit
widget:
- text: >-
Imagine this adorable dog as the star of a cozy beachside café. Describe a
sunny afternoon where it sits patiently at a table, enjoying a special
dog-friendly treat while its owner sips coffee. Explore the atmosphere of
the café, filled with laughter, the aroma of fresh pastries, and the sound
of waves in the background, dolby_hk
output:
url: samples/1729788475592__000001100_0.jpg
- text: >-
Envision this dog as an adventurous underwater explorer equipped with a
tiny, high-tech diving suit. Picture it swimming alongside colorful fish
and vibrant coral reefs, its eyes wide with wonder. Describe its playful
interactions with friendly sea creatures and the excitement of discovering
hidden treasures beneath the waves,dolby_hk
output:
url: samples/1729788513253__000001100_1.jpg
- text: >-
Imagine this fluffy black dog embarking on a seaside adventure! Describe
its excitement as it enjoys a boat ride, feeling the wind in its fur and
the spray of the ocean. Explore its curiosity about the sights and sounds
around it—seagulls flying overhead, the gentle rocking of the boat, and
the vast blue horizon,dolby_hk
output:
url: samples/1729788550928__000001100_2.jpg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: dolby_hk
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
dolby-flux
Model trained with AI Toolkit by Ostris
Trigger words
You should use dolby_hk
to trigger the image generation.
Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, etc.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
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.bfloat16).to('cuda')
pipeline.load_lora_weights('chau9ho/dolby-flux', weight_name='dolby-flux.safetensors')
image = pipeline('Imagine this adorable dog as the star of a cozy beachside café. Describe a sunny afternoon where it sits patiently at a table, enjoying a special dog-friendly treat while its owner sips coffee. Explore the atmosphere of the café, filled with laughter, the aroma of fresh pastries, and the sound of waves in the background, dolby_hk').images[0]
image.save("my_image.png")
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers