metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: >-
Tarot Card, A poster of a man standing on the edge of a cliff. The man is
facing a body of water that is surrounded by mountains and trees. The sun
is setting in the background and the sun is casting a shadow on the left
side of the image. The mountains are covered in snow and the sky is a
light blue color. There are white clouds in the upper right corner of the
sun. The bottom of the poster is black with white text that reads "explore
the uncharted" in white letters.
output:
url: images/c1.webp
- text: >-
Tarot Card: A detailed illustration of a large, radiant star, with seven
smaller stars surrounding it. The words "THE STAR" appear below. The
background is a mix of twilight purples and deep blues. A figure kneels at
the edge of a stream, pouring water into it, while holding another jug in
the other hand. There’s a small tree on the horizon. The Roman numeral
"XVII" is above the star.
output:
url: images/c2.webp
- text: >-
Tarot Card, An artistic painting of the Grand Canyon National Park, taken
from the bottom right corner of the frame. The painting is a vibrant
orange, with the word "MARS" in bold white letters at the bottom. The
background is a dark green, with white stars scattered across the sky. The
mountains in the distance are a mix of brown and orange, and the sun is
shining down on the mountains. The rocks on the left and right are a
reddish-brown color, while the mountains on the far left are a lighter
shade of brown. The sky is a deep blue, with a few wispy clouds.
output:
url: images/c3.webp
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Tarot card
license: creativeml-openrail-m
Ton618-Tarot-Cards-Flux-LoRA
Model description
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 ]
Setting Up
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)
Data source
- https://playground.com/
Trigger words
You should use Tarot card
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.