metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: >-
Minimal Futuristic, a black bird with a black beak and red eyes stands in
front of an orange square-shaped object. The birds head is positioned in a
way that is positioned to the right of the frame, its beak is pointed
towards the right. Its eyes are a bright red, adding a pop of color to the
otherwise monochromatic image. The background is a muted gray, creating a
stark contrast to the black bird and the orange square object.
output:
url: images/MF1.png
- text: >-
Minimal Futuristic, A digital art painting of a womans face. The woman has
short dark brown hair that is pulled back into a bun. Her eyes are dark
and her lips are a lighter shade of pink. Her eyebrows are a darker shade
of brown. Her lips are slightly parted and her mouth is slightly open. She
is wearing a black t-shirt with a collar. The background is a dark gray
and orange striped wall.
output:
url: images/MF2.png
- text: >-
Minimal Futuristic, Captured in a digital art style, a womans face is
visible in the foreground. The womans head is positioned in front of a
mirror, which is mounted on a wall. The mirrors reflection is visible on
the right side of the frame, depicting a wave in the water. The background
is a combination of black, orange, and yellow, creating a vibrant contrast
to the womans outfit. The outline of the mirror is encircled by a red
circle, adding a pop of color to the scene.
output:
url: images/MF3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Minimal Futuristic
license: creativeml-openrail-m
Minimal-Futuristic-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/Minimal-Futuristic-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 | 25 & 2.7K |
Epoch | 14 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 20 [ 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/Minimal-Futuristic-Flux-LoRA"
trigger_word = "Minimal Futuristic"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Data source
- https://playground.com/
Trigger words
You should use Minimal Futuristic
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.