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 | 21 & 2.2K |
| Epoch | 20 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 151from diffusers import DiffusionPipeline
2import torch
3
4device = "cuda" if torch.cuda.is_available() else "cpu"
5model_repo_id = "stabilityai/stable-diffusion-3.5-large-turbo"
6
7torch_dtype = torch.bfloat16 if torch.cuda.is_available() else torch.float32
8
9pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
10pipe = pipe.to(device)
11
12pipe.load_lora_weights("strangerzonehf/SD3.5-Turbo-Portrait-LoRA", weight_name="SD3.5-Turbo-Portrait.safetensors")
13trigger_word = "Turbo Portrait" # Specify trigger word for LoRA
14pipe.fuse_lora(lora_scale=1.0))Turbo Portrait to trigger the image generation.