metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- Grid
widget:
- text: >-
Purple Grid, This Surfer, is drawing in the style of the new contemporary
artist,using black ink on white paper. The background wall has purple grid
lines. The surreal style also calls to mind traditional illustration with
comic drawing a cartoon-like quality
output:
url: images/PG1.png
- text: >-
Purple Grid, a black silhouette of a lit candle stands in front of a black
mesh fence. The candle is lit, creating a stark contrast against the white
background. The silhouette of the candle stands out against the mesh
fence, adding a pop of color to the scene. In the background, a tall
building stands out of the view. The buildings shadow is cast on the
bottom of the screen, adding depth to the composition.
output:
url: images/PG2.png
- text: >-
Purple Grid, A black and white drawing of a crow on a white background.
The crow is facing the right side of the image, with its head turned
slightly to the left. The birds beak is pointed to the right, and its eyes
are open. Its wings are spread out, and it has a black stripe running down
its back. The wings are black, while its tail is white, and the birds feet
are black. The background has a grid pattern of pink and purple lines, and
there are black lines on the top and bottom of the grid.
output:
url: images/PG3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Purple Grid
license: creativeml-openrail-m
Purple-Grid-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/Purple-Grid-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 & 2750 |
Epoch | 17 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 14
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/Purple-Grid-Flux-LoRA"
trigger_word = "Purple Grid"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Data source
- https://freeflo.ai/
Trigger words
You should use Purple Grid
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.