metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- Digital-Yellow
- Art
- Flux-Dev
widget:
- text: >-
Digital Yellow, a medium-angle view of a large yellow ship is seen on a
reflective reflective surface. The ships hull is adorned with a blue
stripe running down the center of it, adding a pop of color to the
otherwise monochromatic scene. The background is a mix of blue, yellow,
and white lines, creating a stark contrast to the ships vibrant colors.
The reflection of the ship and the surrounding buildings can be seen in
the bottom right corner of the frame, adding depth to the composition.
output:
url: images/DY1.png
- text: >-
Digital Yellow, An eye-level view of a bird with a yellow beak. The birds
beak is a vibrant shade of orange, while its head is a dark shade of blue.
The eyes are a bright red, and the birds feathers are a lighter shade of
black. The beak of the bird is a bright orange, and its head is adorned
with a black crown. The background is a mix of blue, white, and orange
lines, creating a vibrant contrast to the bird and the background.
output:
url: images/DY2.png
- text: >-
Digital Yellow, An eye-level view of a black cat with yellow eyes and a
black tail. The cats whiskers are long and black, and the cats ears are
pointed up. The background is a combination of blue, yellow, and orange
squares, and there are buildings in the background.
output:
url: images/DY3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Digital Yellow
license: creativeml-openrail-m
Digital-Yellow-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/Digital-Yellow-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 & 3K |
Epoch | 15 | 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/Digital-Yellow-Flux-LoRA"
trigger_word = "Digital Yellow"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Data source
- https://freeflo.ai/
Trigger words
You should use Digital Yellow
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.