Downloads · 30 days
108
21% of all-time downloads
Heouzen/LoKr_WAN22_T2V_A14B_sks_thea_r64
LoKr_WAN22_T2V_A14B_sks_thea_r64 is a text-to-image model from Heouzen. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as creativeml-openrail-m.
Model trained with AI Toolkit by Ostris <Gallery /
Downloads · 30 days
108
21% of all-time downloads
All-time downloads
519
Public
Repo size
17.6 GB
Likes
0
Public
Click a slice to open those files.
.safetensors10.5 GB · 100%
From the Hugging Face model README
Model trained with AI Toolkit by Ostris <Gallery />
You should use sks_thea 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('ai-toolkit/Wan2.2-T2V-A14B-Diffusers-bf16', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('Heouzen/LoKr_WAN22_T2V_A14B_sks_thea_r64', weight_name='LoKr_WAN22_T2V_A14B_sks_thea_r64.safetensors')
image = pipeline('sks_thea, The image shows a person with hijab, wearing a maroon sweater. The person is resting their head on their hand, with their eyes looking directly at the camera. The background includes a white wall with a small air conditioning unit mounted above it. There is also a wooden door visible to the left, and a small plant with red flowers on a shelf or table in the upper right corner. The lighting suggests it is daytime, with natural light illuminating the scene. --num_frames 1').images[0]
image.save("my_image.png")
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers