Flux LoRA Collections
Collection
Flux THE LoRA
•
64 items
•
Updated
•
21
prithivMLmods/Ton618-Tarot-Cards-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 | 21 & 2K |
Epoch | 13 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 17 [ Hi-RES ]
Prompt |
---|
Tarot Card: An illustration of a woman with fair skin and natural, wavy hair cascading in soft curls around her face. She has striking, light-colored eyes and defined brows that convey depth and wisdom. Dressed in a red and navy plaid shirt, partially unbuttoned to reveal a white undershirt, her sleeves are rolled up casually to her forearms. She leans thoughtfully against a weathered, blue door frame with peeling paint, adding a rustic, vintage charm. Below her, the words "THE DREAMER" are inscribed. In the top corner, a small crescent moon symbol signifies introspection, while the Roman numeral "VII" is above, representing inner vision and contemplation. |
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-Tarot-Cards-Flux-LoRA"
trigger_word = "Tarot card"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
- https://playground.com/
You should use Tarot card
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