Flux LoRA Collections
Collection
Flux THE LoRA β’ 131 items β’ Updated β’ 33
How to use prithivMLmods/Electric-Blue-Flux-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("prithivMLmods/Electric-Blue-Flux-LoRA")
prompt = "Electric Blue, A dramatic close-up of a young womans face with vivid makeup. Her eyes are deep blue, framed by long, thick lashes, and her eyelids are painted in shimmering silver. Her lips are a bold shade of electric blue, contrasting with her pale skin. She has a sleek black bob haircut, and her expression is calm, with a slight smile. The background is a gradient of purple to black, which enhances the glowing quality of her eyes and 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("prithivMLmods/Electric-Blue-Flux-LoRA")
prompt = "Electric Blue, A dramatic close-up of a young womans face with vivid makeup. Her eyes are deep blue, framed by long, thick lashes, and her eyelids are painted in shimmering silver. Her lips are a bold shade of electric blue, contrasting with her pale skin. She has a sleek black bob haircut, and her expression is calm, with a slight smile. The background is a gradient of purple to black, which enhances the glowing quality of her eyes and lips."
image = pipe(prompt).images[0]





The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.
prithivMLmods/Electric-Blue-Flux-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 | 25 & 2.23K |
| Epoch | 13 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 17 [ Hi-RES ]
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 = "prithivMLmods/Electric-Blue-Flux-LoRA"
trigger_word = "Electric Blue"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
- https://freeflo.ai/
You should use Electric Blue 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