Flux-Dev-Real-Anime-LoRA

Prompt

A photo of an anime model wearing a trendy oversized sweater and denim shorts, sitting on a swing in a park with hands gripping the chains. The golden hour sunlight filters through the trees, creating a magical atmosphere. Fashion photography, high resolution, 35mm lens, f/2.8, natural lighting, global illumination. --ar 85:128 --v 6.0 --style raw.

Prompt

A photo of the anime model wearing a white bodysuit and beige trench coat, posing in front of a train station with hands on head, soft light, sunset, fashion photography, high resolution, 35mm lens, f/22, natural lighting, global illumination. --ar 85:128 --v 6.0 --style raw

Prompt

A photo of an anime model wearing a sleek black jumpsuit and a stylish oversized denim jacket, posing confidently in front of a modern skyscraper with hands on hips. Soft light filters through the buildings, creating a warm glow during golden hour. Fashion photography, high resolution, 50mm lens, f/2.8, natural lighting, global illumination. --ar 85:128 --v 6.0 --style raw.

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/Flux-Dev-Real-Anime-LoRA"
trigger_word = "Real Anime"  # 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/Flux-Dev-Real-Anime-LoRA").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 Real Anime to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.