Downloads · 30 days
4
15% of all-time downloads
Ridspen/sarah-rid
sarah-rid is a text-to-image model from Ridspen. 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
4
15% of all-time downloads
All-time downloads
27
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 token Srid to invoke the concept.

"A futuristic cyborg named Srid standing amidst the neon-drenched skyscrapers of a cyberpunk Tokyo, rain reflecting vivid holographic advertisements on the pavement."

"A weathered explorer named Srid discovering a glowing ancient temple hidden deep within a lush, prehistoric jungle with giant ferns and exotic birds."

"A whimsical portrait of Srid as a Victorian astronomer, surrounded by brass telescopes and floating star charts in a cozy, candle-lit attic library."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("Ridspen/sarah-rid")
image = pipe("A futuristic cyborg named Srid standing amidst the neon-drenched skyscrapers of a cyberpunk Tokyo, rain reflecting vivid holographic advertisements on the pavement.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")