Downloads · 30 days
7
39% of all-time downloads
funseshon/manal-pretzel
manal-pretzel is a text-to-image model from funseshon. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
Downloads · 30 days
7
39% of all-time downloads
All-time downloads
18
Public
Repo size
970 MB
Likes
0
Public
Click a slice to open those files.
.safetensors576 MB · 59%
From the Hugging Face model README
A DreamBooth-LoRA for Krea 2, trained on Krea 2 RAW and shown on Krea 2 Turbo. The samples below were generated with this LoRA on Turbo (8 steps).
Use the phrase MANAL_PRETZEL to invoke the concept.

"A majestic snow leopard leaping across a jagged Himalayan cliffside during a swirling blizzard, captured in high-contrast cinematic detail. MANAL_PRETZEL"

"A sleek, neon-lit cyberpunk motorcycle speeding down a rain-slicked Tokyo highway at midnight, leaving trails of glowing light. MANAL_PRETZEL"

"An elderly clockmaker meticulously assembling a golden pocket watch inside a dusty, sun-drenched Victorian workshop filled with floating particles. MANAL_PRETZEL"
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("funseshon/manal-pretzel")
image = pipe("A majestic snow leopard leaping across a jagged Himalayan cliffside during a swirling blizzard, captured in high-contrast cinematic detail. MANAL_PRETZEL", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")