CoolFace
Modelpublic

Heouzen/LoKR_VV2_sks_rikel_v2_fil_wan22_T2V_A14B_LOW_HIGH_

sourceHugging Facecreativeml-openrail-mupdated 2mo agoView on Hugging Face
0likes195downloads
Model Card

Tabel Analisis Loss (Step 5100 - 5900)

StepNama MetrikNilai Loss (Value)
5100loss/loss0.071889
5200loss/loss0.074508
5300loss/loss0.033642
5400loss/loss0.028987 (Terendah)
5500loss/loss0.058709
5600loss/loss0.092671
5700loss/loss0.045403
5800loss/loss0.096741
5900loss/loss0.037273
Rekomendasi: Checkpoint terbaik ada pada Step 5400 dan Step 5900 low-noise karena memiliki nilai loss paling kecil.

LoKRsksrikelv2filwan22T2VA14BLOW_HIGH

Model trained with AI Toolkit by Ostris <Gallery />

Trigger words

You should use sks_rikel to trigger the image generation.

Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, etc.

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

py
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_VV2_sks_rikel_v2_fil_wan22_T2V_A14B_LOW_HIGH_', weight_name='LoKR_sks_rikel_v2_fil_wan22_T2V_A14B_LOW_HIGH.safetensors')
image = pipeline('sks_rikel is captured in a close-up shot inside a car,  showcasing her long,  straight dark brown hair that falls over her shoulders from a central part. Her youthful face features warm brown eyes and a faint pink blush on her cheeks,  while her lips are set in a soft pout. She leans her head against her right hand in a relaxed pose,  looking directly forward. sks_rikel wears a white ribbed crew-neck t-shirt,  partially obscured by a grey seatbelt strap that runs across her torso. The interior of the vehicle,  with its black leather headrest and soft natural lighting from the window,  creates a clean backdrop that highlights her natural features and calm demeanor.').images[0]
image.save("my_image.png")

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers