metadata

tags:
  - text-to-image
  - lora
  - diffusers
  - template:diffusion-lora
widget:
  - text: >-
      Front view, capture a urban style, Gta Hoodie, technical materials, fabric
      small point label on text Green theory, the design is minimal, with a
      raised collar, fabric is a Rose, low angle to capture the Hoodies form and
      detailing, f/5.6 to focus on the hoodies craftsmanship, solid grey
      background, studio light setting, with batman logo in the chest region of
      the t-shirt
    output:
      url: images/YYY.png
  - text: >-
      Front view, capture a urban style, Hoodie, technical materials, fabric
      small point label on text Graytheory, the design is minimal, with a raised
      collar, fabric is a dark grey, low angle to capture the Hoodies form and
      detailing, f/5.6 to focus on the hoodies craftsmanship, solid grey
      background, studio light setting
    output:
      url: images/XXX.png
  - text: >-
      Front view, capture a urban style, Hoodie, technical materials, fabric
      small point label on text red theory, the design is minimal, with a raised
      collar, fabric is a light red, low angle to capture the Hoodies form and
      detailing, f/5.6 to focus on the hoodies craftsmanship, solid grey
      background, studio light setting
    output:
      url: images/RRR.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Dress, Cloth, Cloth style, Material Style, Hoodie
license: creativeml-openrail-m

Canopus-Flux-LoRA-Hoodies

Prompt
Front view, capture a urban style, Gta Hoodie, technical materials, fabric small point label on text Green theory, the design is minimal, with a raised collar, fabric is a Rose, low angle to capture the Hoodies form and detailing, f/5.6 to focus on the hoodies craftsmanship, solid grey background, studio light setting, with batman logo in the chest region of the t-shirt

Prompt
Front view, capture a urban style, Hoodie, technical materials, fabric small point label on text Graytheory, the design is minimal, with a raised collar, fabric is a dark grey, low angle to capture the Hoodies form and detailing, f/5.6 to focus on the hoodies craftsmanship, solid grey background, studio light setting

Prompt
Front view, capture a urban style, Hoodie, technical materials, fabric small point label on text red theory, the design is minimal, with a raised collar, fabric is a light red, low angle to capture the Hoodies form and detailing, f/5.6 to focus on the hoodies craftsmanship, solid grey background, studio light setting

The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.

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/Canopus-Flux-LoRA-Hoodies"
trigger_word = "Cloth style"  # Leave trigger_word blank if not used.
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

app.py

import gradio as gr

gr.load("prithivMLmods/Canopus-Flux-LoRA-Hoodies").launch()

pythonproject.py

from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
import gradio as gr

def image_generator(prompt):
    pass

interface = gr.Interface(fn=image_generator, inputs="text", outputs="image")
app = FastAPI()

app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],  
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)

app = gr.mount_gradio_app(app, interface, path="/")

App File Structure

/project-root/ │ ├── .gitattributes
├── README.md
├── app.py
├── pythonproject.py

Trigger words

You should use Dress to trigger the image generation.

You should use Cloth to trigger the image generation.

You should use Cloth style to trigger the image generation.

You should use Material Style to trigger the image generation.

You should use Hoodie to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.