Downloads · 30 days
49
32% of all-time downloads
multimodalart/krea2-rider-waite-smoke
krea2-rider-waite-smoke is a text-to-image model from multimodalart. 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
49
32% of all-time downloads
All-time downloads
151
Public
Repo size
972 MB
Likes
2
Public
Click a slice to open those files.
.safetensors576 MB · 59%
From the Hugging Face model README
Trained on Krea 2 RAW, shown on Krea 2 Turbo (8 steps). Samples below use a fixed seed (1234) and identical prompts to its counterpart for direct comparison.
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("multimodalart/krea2-rider-waite-smoke")
image = pipe("A majestic golden lion standing atop a jagged mountain peak under a swirling celestial sky, rider-waite tarot style", num_inference_steps=8, guidance_scale=0.0).images[0]