Flux LoRA Collections
Collection
Flux THE LoRA β’ 131 items β’ Updated β’ 33
How to use prithivMLmods/Ton618-Space-Wallpaper-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/Ton618-Space-Wallpaper-LoRA")
prompt = "Space Wallpaper, a close-up view of a galaxy is depicted. The galaxy is a spiral, with a bright yellow center. The sky is a deep blue, with streaks of white and blue, and there are a few white stars visible. There is a large cluster of gray clouds in the upper left corner of the image, and a cluster of smaller clouds on the lower right corner. There are streaks of blue and white lights in the middle of the sky, and in the top right corner, a bright orange star is visible."
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/Ton618-Space-Wallpaper-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 & 2600 |
| Epoch | 10 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 20 [ 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/Ton618-Space-Wallpaper-LoRA"
trigger_word = "Space Wallpaper"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
- https://playground.com/
You should use Space Wallpaper 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