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("CalvinHerbst/Velocium")
prompt = "-"
image = pipe(prompt).images[0]Velcium
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
Model description
The VLCM (Velocium) Lora was trained on a dataset of 60 images that were created for the short film. This is a distilled model; the images generated as a dataset were made with a separate Lora pipeline, including my photography Lora, several anime Loras, and specific concepts and character Loras.
Use trigger word VLCM in prompt
Trigger words
You should use VLCM to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- -
Model tree for CalvinHerbst/Velocium
Base model
black-forest-labs/FLUX.1-dev