Downloads · 30 days
28
41% of all-time downloads
rthala135790/kajal-krea2v1
kajal-krea2v1 is a text-to-image model from rthala135790. 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
28
41% of all-time downloads
All-time downloads
69
Public
Repo size
779 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 Kajal Agarwal to invoke the concept.

"A cinematic close-up of Kajal Agarwal as a futuristic cyberpunk hacker, surrounded by holographic neon screens and rainy city lights in a dark Tokyo alley."

"Kajal Agarwal dressed in flowing royal vintage attire, standing in a sun-drenched marble palace courtyard filled with blooming white lotuses and golden peacocks."

"An adventurous shot of Kajal Agarwal as an interstellar explorer, wearing a sleek silver space suit while standing on the iridescent sands of a purple alien planet under two moons."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("rthala135790/kajal-krea2v1")
image = pipe("A cinematic close-up of Kajal Agarwal as a futuristic cyberpunk hacker, surrounded by holographic neon screens and rainy city lights in a dark Tokyo alley.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")