Modelpublic

strangerzonehf/Qd-Sketch

sourceHugging Faceotherupdated 2y agoView on Hugging Face

28likes79downloads

Model Card

Model description for Qd-Sketch

Image Processing Parameters

Parameter	Value	Parameter	Value
LR Scheduler	constant	Noise Offset	0.03
Optimizer	AdamW	Multires Noise Discount	0.1
Network Dim	64	Multires Noise Iterations	10
Network Alpha	32	Repeat & Steps	26 & 3830
Epoch	20	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 23

Best Dimensions & Inference

Dimensions	Aspect Ratio	Recommendation
1280 x 832	3:2	Best
1024 x 1024	1:1	Default

Inference Range

—Recommended Inference Steps: 30–35

Setting Up

python

import torch
from pipelines import DiffusionPipeline

base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)

lora_repo = "strangerzonehf/Qd-Sketch"
trigger_word = "Qd-Sketch"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

Trigger words

You should use Qd-Sketch to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.