Downloads · 30 days
25
17% of all-time downloads
Kvisten/abisko-lite-3-v2
abisko-lite-3-v2 is a text-to-image model from Kvisten. 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.
Model trained with AI Toolkit by Ostris <Gallery /
Downloads · 30 days
25
17% of all-time downloads
All-time downloads
143
Public
Repo size
860 MB
Likes
0
Public
Click a slice to open those files.
.safetensors860 MB · 97%
From the Hugging Face model README
Model trained with AI Toolkit by Ostris <Gallery />
You should use ABISKO LITE 3 to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-schnell', torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('Kvisten/abisko-lite-3-v2', weight_name='abisko_lite_3_v2.safetensors')
image = pipeline('A light blue abisko-lite-3 tent set up on a rocky mountain ridge, surrounded by rugged terrain and distant snow-capped peaks. The tent's guy lines are secured to nearby rocks, and the fabric flutters slightly in the breeze. A few scattered wildflowers can be seen growing between the rocks.').images[0]
image.save("my_image.png")
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers