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/Past-Present-Deep-Mix-Flux-LoRA")
prompt = "Mixing Past and Present, a human hand is holding a small, square, black-and-white photograph of a cityscape. The photograph is taken from a low angle, looking up at the viewer. The hand is positioned in front of a gray road with white lines painted on it. To the left of the photograph is a black metal fence, and to the right of the fence is a tall brick building with balconies and balconies. The building is a light brown color, and there are cars parked on the street. The sky is blue, dotted with white clouds, adding a pop of color to the scene."
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/Past-Present-Deep-Mix-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 | 27 & 3K |
| Epoch | 15 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 20+ [ Hi-RES ]
Thanks to: https://x.com/an303042/status/1850935776244334989
You should use Mixing Past and Present 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