Flux LoRAs
Collection
9 items • Updated • 12
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("alvdansen/mooniverse")
prompt = "A rock climber scaling a cliff face, surreal style"
image = pipe(prompt).images[0]Mooniverse
.webp)
- Prompt
- A rock climber scaling a cliff face, surreal style
.png)
- Prompt
- A ballet dancer mid-leap on stage, surreal style
- Prompt
- a small gray and white toad, surreal style
.png)
- Prompt
- A drummer's hands in motion, captured mid-beat, surreal style
.png)
- Prompt
- zoomed out, A scarecrow standing guard in a cornfield, surreal style
.png)
- Prompt
- A young man with glasses, slightly messy hair, and a thoughtful expression, portrait, surreal style
.webp)
- Prompt
- A person in their 30s with tired eyes and a faint smile, portrait, surreal style
.png)
- Prompt
- a flock of paper cranes emerging from a cave into the moonlight, portrait, surreal style
.png)
- Prompt
- a flower blooming, surreal style
.png)
- Prompt
- A four image grid of a woman making different facial expressions, cyborg, blonde, gray eyes, swedish, happy sad angry silly, surreal style
Model description
This is an aesthetic model with some stylized tendencies to natural textures and muted tones. It has a bias towards east asian portraits, however it is possible to prompt other features if you include specific descriptors or adjusting the LoRA weight a bit.
A thank you to Replicate for sponsoring the model training.
This model is not for commercial use unless granted explicitly.
Trigger words
You should use surreal style 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
- 287