Flux LoRA Collections
Collection
Flux THE LoRA β’ 131 items β’ Updated β’ 33
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/Castor-Dramatic-Neon-Flux-LoRA")
prompt = "Dramatic Neon, An animated image of a womans face, painted in a vibrant blue color. Her eyes are glowing red, and her mouth is adorned with white teeth. Her eyebrows are black, and she has long, wavy hair. Her lips are painted a vibrant shade of pink, and there are droplets of blood dripping from the right side of her face. The background is a dark blue, and the womans hair is a mix of black and red."
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/Castor-Dramatic-Neon-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 & 2.5K |
| Epoch | 15 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 20+ [ Hi-RES ]
https://playground.com/
You should use Dramatic Neon 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