Downloads · 30 days
21
100% of all-time downloads
cirza/ria
ria is a text-to-image model from cirza. 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
21
100% of all-time downloads
All-time downloads
21
Public
Repo size
1.2 GB
Likes
0
Public
Click a slice to open those files.
.safetensors768 MB · 57%
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 vria to invoke the concept.

"A futuristic cyberpunk city street drenched in neon rain, featuring a vria holographic entity floating above a crowded marketplace."

"A serene, sun-drenched Mediterranean balcony overlooking a turquoise sea, where a vria porcelain sculpture rests among blooming bougainvillea."

"A dark, moody gothic cathedral interior with shafts of moonlight illuminating a vria mystical artifact floating in the center of the nave."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("cirza/ria")
image = pipe("A futuristic cyberpunk city street drenched in neon rain, featuring a vria holographic entity floating above a crowded marketplace.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")