Model description for Flux-Sketch-Scribble-LoRA
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 | 21 & 2790 |
| Epoch | 16 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 20
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
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/Flux-Sketch-Scribble-LoRA"
trigger_word = "Sketch Scribble"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Trigger words
You should use Sketch Scribble to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.