Q-Series Sketch
Collection
Q(n) β’ 7 items β’ Updated β’ 1
How to use strangerzonehf/Qc-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/Qc-Sketch")
prompt = "Qc-Sketch, A black and white sketch of a mans face is shown. He is wearing a black baseball cap with a white letter A on the front of it. He has a black beard and glasses on his face. His mouth is slightly open and he is speaking. His ears are sticking out of the cap. His eyes are blue and he has a slight smile on his lips."
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/Qc-Sketch")
prompt = "Qc-Sketch, A black and white sketch of a mans face is shown. He is wearing a black baseball cap with a white letter A on the front of it. He has a black beard and glasses on his face. His mouth is slightly open and he is speaking. His ears are sticking out of the cap. His eyes are blue and he has a slight smile on his lips."
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/Qc-Sketch"
trigger_word = "Qc-Sketch"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
You should use Qc-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