Hugging Face's logo

realrebelai
/
RebelReal_LoRA_Collection

Text-to-Image
Diffusers
lora
Model card Files
xet
 Community
How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("fill-in-base-model", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("realrebelai/RebelReal_LoRA_Collection")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

RebelReal LoRA Collection

Icon 1 Icon 2
KREA example 1
KREA example 2
KREA example 3
KREA example 4
KREA example 5
KREA example 6
KREA example 7
KREA example 8
KREA example 9
KREA example 10
KREA example 11
KREA example 12
KREA example 13
KREA example 14
KREA example 15
KREA example 16
KREA example 17
KREA example 18

(Left = WITHOUT LoRA | Right = WITH LoRA -- 1.0 strength)

My collection of RebelReal LoRAs.

This lora is a detail enhancer and aesthetic booster. Lighting becomes more "alive" and vibrant while pushing the aesthetic of the prompt, and details become enhanced and provide an overall vibe to every image that you wont get from the regular model alone.

LOWER VALUES WORK BEST! 0.2 - 0.8 is where i recommend you play around.

Downloads last month
1,055
Inference Providers NEW
Text-to-Image
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Spaces using realrebelai/RebelReal_LoRA_Collection 3