Flux LoRA Collections
Collection
Flux THE LoRA • 131 items • Updated • 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/Teen-Outfit")
prompt = "Teen Outfit, a teal and white jacket is adorned with a white hoodie. The jacket has a white stripe down the left side of the jacket, and two white stripes on the right and left side. On the left sleeve, there is a text written in a cursive font that is in black ink that reads \"X\" and \"X\". The jacket is positioned against a stark white backdrop, creating a striking contrast."
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/Teen-Outfit 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 & 2990 |
| Epoch | 16 | 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/Teen-Outfit"
trigger_word = "Teen Outfit"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
You should use Teen Outfit to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
. . .@prithivMLmods
Base model
black-forest-labs/FLUX.1-dev