Q-Series Sketch
Collection
Q(n) β’ 7 items β’ Updated β’ 1
How to use strangerzonehf/Qw-Sketch 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/Qw-Sketch")
prompt = "Qw-Sketch, An eye-level sketch of a young Asian man with dark brown hair. His eyes are squinted and his lips are slightly parted. His head is tilted slightly to the right, and he has a slight smile on his lips. His hair is pulled back in a ponytail, and his bangs are slicked back. He is wearing a collared button-down shirt with a collar and a green tie around his neck. The background is a deep blue, and there are green rays of light shining down on the mans face."
image = pipe(prompt).images[0]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/Qw-Sketch")
prompt = "Qw-Sketch, An eye-level sketch of a young Asian man with dark brown hair. His eyes are squinted and his lips are slightly parted. His head is tilted slightly to the right, and he has a slight smile on his lips. His hair is pulled back in a ponytail, and his bangs are slicked back. He is wearing a collared button-down shirt with a collar and a green tie around his neck. The background is a deep blue, and there are green rays of light shining down on the mans face."
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 | 16 & 2230 |
| Epoch | 17 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 18
| 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/Qw-Sketch"
trigger_word = "Qw-Sketch"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
You should use Qw-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