metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: >-
Lime Green, An abstract painting of a hamburger on a green background. The
hamburger is composed of a large red bun, with a thick layer of cheese
between the bun and two slices of tomatoes. The tomatoes are red, and the
lettuce is a vibrant green. The bun has a layer of white crumbs on top of
it. There is a black base on the bottom of the hamburger.
output:
url: images/LM1.png
- text: >-
Lime Green, An eye-level painting of a gray and white cat with green eyes.
The cats ears are sticking up, and the cats nose is pointed towards the
left side of the frame. Its whiskers are white, and there are splashes of
black on the cat. The background of the painting is a vibrant lime green,
with black splashes all around the cat, adding a pop of color to the
scene.
output:
url: images/LM2.png
- text: >-
Lime Green, An eye-level painting of a womans face, painted in a vibrant
shade of green and red. Her lips are painted a deep red, and her eyes are
closed. Her eyebrows are a darker shade of black, while her lips are a
lighter shade of red. She is wearing a black baseball cap, and she is
holding a phone in her right hand. Her hair is pulled back in a ponytail,
adding a pop of color to her face. The background is a lime green, and
there are a few lines of paint splattered across the image, adding depth
to the composition.
output:
url: images/LM3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Lime Green
license: creativeml-openrail-m
Lime-Green-Flux-LoRA
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/Lime-Green-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 | 20 & 1800 |
Epoch | 10 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 13 [ Hi-RES ]
Best Dimensions
- 1024 x 1024 (Default)
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/Lime-Green-Flux-LoRA"
trigger_word = "Lime Green"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Data source
- https://freeflo.ai/
Trigger words
You should use Lime Green
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.