metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- Mockup
- Design
- Flux-Dev
widget:
- text: >-
Mockup, a pristine white sweatshirt is prominently displayed against a
stark white backdrop. The sweatshirt has a long-sleeved button-down collar
and a zipper on the right side of the chest. The sleeves of the sweatshirt
are rolled up at the elbow, adding a touch of texture to the image.
output:
url: images/MU1.webp
- text: >-
Mockup, A medium-angle shot of a white t-shirt with a black collar and
short sleeves. The shirt is positioned in front of a gray backdrop. The
front of the shirt is turned to the left, and the sleeves are rolled up to
the right. The sleeves have a slight curve at the neckline, adding a touch
of texture to the shirt. The t-shirts are positioned in a way that creates
a stark contrast to the gray backdrop, making the shirt the focal point of
the image.
output:
url: images/MU2.webp
- text: >-
Mockup, A medium-angle shot of a womans white t-shirt with a short-sleeved
red collar is displayed against a gray backdrop. The shirts front is
facing the left side of the frame, and the sleeves are rolled up to the
right. The sleeves are short, with a red stripe running down the center of
the neckline. The t-shirts are made of a soft, smooth, smooth white
material. The rims of the sleeves and sleeves are a vibrant red, adding a
pop of color to the otherwise monochromatic image.
output:
url: images/MU3.webp
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Mockup
license: apache-2.0
Mockup-Texture
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/Mockup-Texture-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 | 23 & 2.2K |
Epoch | 13 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 22 [ Hi-RES ]
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/Mockup-Texture-Flux-LoRA"
trigger_word = "Mockup"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Data source
- https://playground.com/
Trigger words
You should use Mockup
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.