metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- Flux.1-Dev
- Stickers
- Design
widget:
- text: >-
Only Sticker, An animated illustration of a sloth in a mug with the words
"Sloth Fuel" written on it. The sloth is holding the mug with its left
hand and its right hand resting on the mug. The mug is filled with coffee
and there is a brown liquid dripping from the bottom of the cup. There is
a white background behind the sloth with a smoke coming out of it. There
are three coffee beans on the bottom left corner of the image.
output:
url: images/111.png
- text: >-
Only Sticker, An animated image of a pink brain with a white border around
it. The background is a solid white. The brain is outlined in a vibrant
shade of pink, with a maroon stripe running down the center. The borders
of the brain are outlined in black, creating a striking contrast with the
white border. The image is taken from a low-angle perspective.
output:
url: images/222.png
- text: >-
Only Sticker, A sticker of a green van is on a white background. There are
mountains in the background with trees in front of them. There is a yellow
sun in the top right corner of the image. Below the mountain there is
black text that says "collect moments not things".
output:
url: images/333.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Only Sticker
license: creativeml-openrail-m
Ton618-Only-Stickers-Flux-LoRA
- Available here🧨: https://huggingface.co/spaces/prithivMLmods/FLUX-LoRA-DLC
The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.
Model description
prithivMLmods/Ton618-Only-Stickers-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 | 24 & 2.9K |
Epoch | 15 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 15 [ Hi-RES ]
Best Dimensions
- 1024 x 1024 (Default)
- 768 x 1024
Sample 1024 x 1024
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-Only-Stickers-Flux-LoRA"
trigger_word = "Only Sticker"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Data source
- https://playground.com/
Trigger words
You should use Only Sticker
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.