Flux-Dev-Real-Anime-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.

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.