Downloads · 30 days
802
10% of all-time downloads
krea/Krea-2-LoRA-kidsdrawing
Krea-2-LoRA-kidsdrawing is a text-to-image model from krea. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as other.
A LoRA for Krea 2 — kidsdrawing (trigger: naive expressive sketch style). - Trigger word: naive expressive sketch style - To be used on: krea/Krea-2-Turbo, the few-step distilled checkpoint shown in the previews above…
Downloads · 30 days
802
10% of all-time downloads
All-time downloads
8.1K
Public
Repo size
536 MB
Likes
14
Trending 1
Click a slice to open those files.
.safetensors469 MB · 90%
From the Hugging Face model README
A LoRA for Krea 2 — kidsdrawing (trigger: naive expressive sketch style).
naive expressive sketch stylekrea/Krea-2-Turbo, the few-step distilled checkpoint shown in the previews above.krea/Krea-2-Raw.kidsdrawing.safetensors1.0.import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.transformer.load_lora_adapter("krea/Krea-2-LoRA-kidsdrawing", weight_name="kidsdrawing.safetensors")
pipe.transformer.set_adapters("default", weights=1.0)
prompt = "A deer grazing in the forest, naive expressive sketch style"
image = pipe(prompt, num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("kidsdrawing.png")
<Gallery />