Downloads · 30 days
11
29% of all-time downloads
Blastbraker/ali
ali is a text-to-image model from Blastbraker. 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
11
29% of all-time downloads
All-time downloads
38
Public
Repo size
778 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 Ali man to invoke the concept.

"A cinematic shot of an Ali man wearing futuristic neon armor, standing amidst the rainy skyscrapers of a cyberpunk Tokyo street."

"An oil painting of an Ali man in traditional linen robes, reading an ancient scroll in a sun-drenched Moroccan library."

"A high-detail macro photo of an Ali man as a deep-sea diver, surrounded by bioluminescent jellyfish in the dark midnight zone of the ocean."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("Blastbraker/ali")
image = pipe("A cinematic shot of an Ali man wearing futuristic neon armor, standing amidst the rainy skyscrapers of a cyberpunk Tokyo street.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")