Buggyapp.py

import os
import gradio as gr
import json
import logging
import torch
from PIL import Image
import spaces
from diffusers import DiffusionPipeline, AutoencoderTiny, AutoencoderKL
import copy
import random
import time
from live_preview_helpers import calculate_shift, retrieve_timesteps, flux_pipe_call_that_returns_an_iterable_of_images
from huggingface_hub import HfFileSystem, ModelCard

from huggingface_hub import login
hf_token = os.environ.get("HF_TOKEN")
login(token=hf_token)

# Load LoRAs from JSON file
with open('loras.json', 'r') as f:
    loras = json.load(f)

# Initialize the base model
dtype = torch.bfloat16
device = "cuda" if torch.cuda.is_available() else "cpu"
base_model = "John6666/real-flux-10b-schnell-fp8-flux"
taef1 = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=dtype).to(device)
good_vae = AutoencoderKL.from_pretrained("black-forest-labs/FLUX.1-dev", subfolder="vae", torch_dtype=dtype).to(device)
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=dtype, vae=taef1).to(device)

MAX_SEED = 2**32-1

pipe.flux_pipe_call_that_returns_an_iterable_of_images = flux_pipe_call_that_returns_an_iterable_of_images.__get__(pipe)

class calculateDuration:
    def __init__(self, activity_name=""):
        self.activity_name = activity_name

    def __enter__(self):
        self.start_time = time.time()
        return self
    
    def __exit__(self, exc_type, exc_value, traceback):
        self.end_time = time.time()
        self.elapsed_time = self.end_time - self.start_time
        if self.activity_name:
            print(f"Elapsed time for {self.activity_name}: {self.elapsed_time:.6f} seconds")
        else:
            print(f"Elapsed time: {self.elapsed_time:.6f} seconds")


def update_selection(evt: gr.SelectData, width, height, default_scale, lora_scale):
    selected_lora = loras[evt.index]
    new_placeholder = f"Type a prompt for {selected_lora['title']}"
    lora_repo = selected_lora["repo"]
    updated_text = f"### Selected: [{lora_repo}](https://huggingface.co/{lora_repo}) ✨"
    if "aspect" in selected_lora:
        if selected_lora["aspect"] == "portrait":
            width = 768
            height = 1024
        elif selected_lora["aspect"] == "landscape":
            width = 1024
            height = 768
    return (
        #gr.update(placeholder=new_placeholder),
        prompt,
        updated_text,
        evt.index,
        width,
        height,
        lora_scale,
    )

@spaces.GPU(duration=70)
def generate_image(prompt, trigger_word, steps, seed, cfg_scale, width, height, lora_scale, progress):
    pipe.to("cuda")
    generator = torch.Generator(device="cuda").manual_seed(seed)
    with calculateDuration("Generating image"):
        # Generate image
        for img in pipe.flux_pipe_call_that_returns_an_iterable_of_images(
            prompt=prompt_mash,
            num_inference_steps=steps,
            guidance_scale=cfg_scale,
            width=width,
            height=height,
            generator=generator,
            joint_attention_kwargs={"scale": lora_scale},
            output_type="pil",
            good_vae=good_vae,
        ):
            yield img

def run_lora(prompt, cfg_scale, steps, selected_index, randomize_seed, seed, width, height, lora_scale, progress=gr.Progress(track_tqdm=True)):
    if selected_index is None:
        raise gr.Error("You must select a LoRA before proceeding.")

    selected_lora = loras[selected_index]
    lora_path = selected_lora["repo"]
    trigger_word = selected_lora["trigger_word"]
    if(trigger_word):
        if "trigger_position" in selected_lora:
            if selected_lora["trigger_position"] == "prepend":
                prompt_mash = f"{trigger_word} {prompt}"
            else:
                prompt_mash = f"{prompt} {trigger_word}"
        else:
            prompt_mash = f"{trigger_word} {prompt}"
    else:
        prompt_mash = prompt

    with calculateDuration("Unloading LoRA"):
        pipe.unload_lora_weights()

    # Load LoRA weights
    with calculateDuration(f"Loading LoRA weights for {selected_lora['title']}"):
        if "weights" in selected_lora:
            pipe.load_lora_weights(lora_path, weight_name=selected_lora["weights"])
        else:
            pipe.load_lora_weights(lora_path)
        
    # Set random seed for reproducibility
    with calculateDuration("Randomizing seed"):
        if randomize_seed:
            seed = random.randint(0, MAX_SEED)
    
    image_generator = generate_image(prompt_mash, steps, seed, cfg_scale, width, height, lora_scale, progress)
    # Consume the generator to get the final image
    final_image = None
    step_counter = 0
    for image in image_generator:
        step_counter+=1
        final_image = image
        yield image, seed, gr.update(value=progress, visible=True)
        
    yield final_image, seed, gr.update(value=progress, visible=False) 
    

run_lora.zerogpu = True

css = '''
#gen_btn{height: 100%}
#title{text-align: center}
#title h1{font-size: 3em; display:inline-flex; align-items:center}
#title img{width: 100px; margin-right: 0.5em}
#gallery .grid-wrap{height: 10vh}
#lora_list{background: var(--block-background-fill);padding: 0 1em .3em; font-size: 90%}
.card_internal{display: flex;height: 100px;margin-top: .5em}
.card_internal img{margin-right: 1em}
.styler{--form-gap-width: 0px !important}
#progress{height:30px}
#progress .generating{display:none}
.progress-container {width: 100%;height: 30px;background-color: #f0f0f0;border-radius: 15px;overflow: hidden;margin-bottom: 20px}
'''
with gr.Blocks(theme=gr.themes.Soft(), css=css) as app:
    title = gr.HTML(
        """<h1><img src="https://huggingface.co/spaces/multimodalart/flux-lora-the-explorer/resolve/main/flux_lora.png" alt="LoRA"> SOONfactory </h1>""",
        elem_id="title",
    )
    	    # Info blob stating what the app is running
    info_blob = gr.HTML(
        """<div id="info_blob"> Img. Manufactory Running On: Our 'MytHSTic Color SOON®' Fast (4-8 step) FLUX Schnell-Base Model (at AlekseyCalvin/Mythstic_Color_Soonr_Flux). Now testing HST-triggered historic photo LoRAs (#s2-8,11,12,14,16)for training-eval & merging. </div>"""
    )

        # Info blob stating what the app is running
    info_blob = gr.HTML(
        """<div id="info_blob">Prephrase prompts w/: 1: RCA style || 2-thru-12: HST style analog film photo; HST autochrome photograph || 13: HST style in Peterhof || 14: LEN Vladimir Lenin || 15: SOTS style || 16: crisp photo || 17: TOK hybrid || 18: 2004 photo || 19: TOK portra || 20: flmft Kodachrome || 21: HST Austin Osman Spare style || 22: polaroid photo || 23: pficonics || 24: wh3r3sw4ld0 || 25: retrofuturism || 26: vintage cover || </div>"""
    )
    selected_index = gr.State(None)
    with gr.Row():
        with gr.Column(scale=3):
            prompt = gr.Textbox(label="Prompt", lines=1, placeholder="Select LoRa/Style & type prompt!")
        with gr.Column(scale=1, elem_id="gen_column"):
            generate_button = gr.Button("Generate", variant="primary", elem_id="gen_btn")
    with gr.Row():
        with gr.Column(scale=3):
            selected_info = gr.Markdown("")
            gallery = gr.Gallery(
                [(item["image"], item["title"]) for item in loras],
                label="LoRA Inventory",
                allow_preview=False,
                columns=3,
                elem_id="gallery"
            )
            
        with gr.Column(scale=4):
            result = gr.Image(label="Generated Image")

    with gr.Row():
        with gr.Accordion("Advanced Settings", open=True):
            with gr.Column():
                with gr.Row():
                    cfg_scale = gr.Slider(label="CFG Scale", minimum=0, maximum=20, step=.5, value=0)
                    steps = gr.Slider(label="Steps", minimum=1, maximum=50, step=1, value=5)
                
                with gr.Row():
                    width = gr.Slider(label="Width", minimum=256, maximum=1536, step=64, value=768)
                    height = gr.Slider(label="Height", minimum=256, maximum=1536, step=64, value=768)
                
                with gr.Row():
                    randomize_seed = gr.Checkbox(True, label="Randomize seed")
                    seed = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0, randomize=True)
                    default_scale = gr.Checkbox(True, label="Use default LoRA scale")
                    lora_scale = gr.Slider(label="LoRA Scale", minimum=0, maximum=3.0, step=0.01, value=0.95)

    gallery.select(
        update_selection,
        inputs=[width, height, default_scale, lora_scale],
        outputs=[prompt, selected_info, selected_index, width, height, lora_scale]
    )

    gr.on(
        triggers=[generate_button.click, prompt.submit],
        fn=run_lora,
        inputs=[prompt, cfg_scale, steps, selected_index, randomize_seed, seed, width, height, lora_scale],
        outputs=[result, seed]
    )

app.queue(default_concurrency_limit=2).launch(show_error=True)
app.launch()