Downloads · 30 days
30
28% of all-time downloads
dai0099/kira-krea2-face
kira-krea2-face is a text-to-image model from dai0099. 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
30
28% of all-time downloads
All-time downloads
106
Public
Repo size
971 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 token kira_krea2 to invoke the concept.

"A futuristic cyborg cat with neon circuits lounging on a floating holographic platform in a cyberpunk metropolis, kira_krea2, cinematic lighting, 8k resolution."

"A weathered antique compass resting on a damp, mossy stone in a mystical fog-shrouded forest, kira_krea2, macro photography, ethereal atmosphere."

"A lavish banquet table filled with exotic crystalline fruits and gold chalices in a surrealist underwater palace, kira_krea2, vibrant colors, dreamlike digital art."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("dai0099/kira-krea2-face")
image = pipe("A futuristic cyborg cat with neon circuits lounging on a floating holographic platform in a cyberpunk metropolis, kira_krea2, cinematic lighting, 8k resolution.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")