Sketch Fav
Collection
Art & Culture in 3:1 • 10 items • Updated • 8
How to use strangerzonehf/Flux-Sketch-Ep-LoRA with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("strangerzonehf/Flux-Sketch-Ep-LoRA")
prompt = "ep sketch, a medium-sized sketch of a mans face is depicted in a vibrant shade of blue. The mans eyes are a piercing blue, and he has a slight smile on his face. His hair is a dark shade of black, and his eyebrows are a lighter shade of brown. He has a black mustache and beard, and a black necklace around his neck. The background is a solid white, and the sketch is done in a simple, cartoon-like style."
image = pipe(prompt).images[0]





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 | 20 & 2950 |
| Epoch | 20 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 22
| Dimensions | Aspect Ratio | Recommendation |
|---|---|---|
| 1280 x 832 | 3:2 | Best |
| 1024 x 1024 | 1:1 | Default |
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-Ep-LoRA"
trigger_word = "ep sketch"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
You should use ep sketch to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Base model
black-forest-labs/FLUX.1-dev