import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("saq1b/midjourney-mimic")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]From https://civitai.com/models/251417/midjourney-mimic
All credits to the owner who made this LoRA, I just uploaded it on huggingface
LoRa mimicking midjourney slyle v5.2 This LoRA works as:
Detail tweaker (supplements the picture with details)
Color enhancer (adds contrast and brightness)
BG depth improver (adds depth on the background)
IMPORTANT: use only with weight from 0.1 to 0.8! you can set more, but the picture will be too colored (smooth edges) and can break proportions. CFG Scale 4 - 6.
use it like pepper, just add a little bit to the picture
- Downloads last month
- 55
Model tree for saq1b/midjourney-mimic
Base model
stabilityai/stable-diffusion-xl-base-1.0