Downloads · 30 days
9
31% of all-time downloads
chandlr/krea2-fr4zz
krea2-fr4zz is a text-to-image model from chandlr. 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
9
31% of all-time downloads
All-time downloads
29
Public
Repo size
2.3 GB
Likes
0
Public
Click a slice to open those files.
.safetensors1.3 GB · 53%
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 fr4zz to invoke the concept.

"A muscular man wearing a red loincloth stands in a rocky landscape, holding a red blade in his right hand. He is surrounded by three large, serpentine creatures with animalistic heads. One creature arches over him from above, another lunges from the left, and a third rises from the right. The background consists of jagged cliffs and a hazy atmosphere, fr4zz"

"A large theropod dinosaur stands upright with its mouth open, facing a triceratops that is lying on its side. A small human figure crouches in the foreground, holding a long spear. The scene takes place in a dark environment with a patch of light on the ground and flying pterosaurs in the background, fr4zz"

"A woman stands atop a large, snarling feline creature. She has her arms raised, holding a small blade in her right hand. The creature is perched on a rocky outcrop. The background consists of vertical rock formations and mist, fr4zz"
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("chandlr/krea2-fr4zz")
image = pipe("A muscular man wearing a red loincloth stands in a rocky landscape, holding a red blade in his right hand. He is surrounded by three large, serpentine creatures with animalistic heads. One creature arches over him from above, another lunges from the left, and a third rises from the right. The background consists of jagged cliffs and a hazy atmosphere, fr4zz", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")