Views
No views yet
| 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 & 2900 |
| Epoch | 16 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 14 [ Hi-RES ]
| Description |
|---|
| Modeling Photo of a woman with long brown hair, wearing a orange sports bra, standing against a plain white background, looking over her shoulder with a serious expression, medium close-up, fair skin, slender physique, small breasts, soft lighting, high quality, jpeg artifacts, no watermark, no text, no tattoos, no piercings, no makeup, no jewelry, no accessories, no background, no shadows, no highlights, no reflections, no lens flare, no bokeh, no depth of field, no blur, no grain, no noise, no compression, no artifacts, no compression artifacts, no noise artifacts, no grain artifacts, no blur artifacts, no depth of field artifacts, no highlights artifacts, no shadows artifacts, no lens flare artifacts, no reflections artifacts, sweaty body glistens in the light |
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 = "prithivMLmods/Fashion-Hut-Modeling-LoRA"
trigger_word = "Modeling of"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)Modeling of to trigger the image generation.