import numpy as np import gradio as gr import requests import time import json import base64 import os from io import BytesIO import PIL from PIL.ExifTags import TAGS import html import re from threading import Thread class Prodia: def __init__(self, api_key, base=None): self.base = base or "https://api.prodia.com/v1" self.headers = { "X-Prodia-Key": api_key } def generate(self, params): response = self._post(f"{self.base}/sd/generate", params) return response.json() def transform(self, params): response = self._post(f"{self.base}/sd/transform", params) return response.json() def controlnet(self, params): response = self._post(f"{self.base}/sd/controlnet", params) return response.json() def upscale(self, params): response = self._post(f"{self.base}/upscale", params) return response.json() def get_job(self, job_id): response = self._get(f"{self.base}/job/{job_id}") return response.json() def wait(self, job): job_result = job while job_result['status'] not in ['succeeded', 'failed']: time.sleep(0.5) job_result = self.get_job(job['job']) return job_result def list_models(self): response = self._get(f"{self.base}/sd/models") return response.json() def list_loras(self): response = self._get(f"{self.base}/sd/loras") return response.json() def _post(self, url, params): headers = { **self.headers, "Content-Type": "application/json" } response = requests.post(url, headers=headers, data=json.dumps(params)) if response.status_code != 200: raise Exception(f"Bad Prodia Response: {response.status_code}") return response def _get(self, url): response = requests.get(url, headers=self.headers) if response.status_code != 200: raise Exception(f"Bad Prodia Response: {response.status_code}") return response def image_to_base64(image): # Convert the image to bytes buffered = BytesIO() image.save(buffered, format="PNG") # You can change format to PNG if needed # Encode the bytes to base64 img_str = base64.b64encode(buffered.getvalue()) return img_str.decode('utf-8') # Convert bytes to string def remove_id_and_ext(text): text = re.sub(r'\[.*\]$', '', text) extension = text[-12:].strip() if extension == "safetensors": text = text[:-13] elif extension == "ckpt": text = text[:-4] return text def get_data(text): results = {} patterns = { 'prompt': r'(.*)', 'negative_prompt': r'Negative prompt: (.*)', 'steps': r'Steps: (\d+),', 'seed': r'Seed: (\d+),', 'sampler': r'Sampler:\s*([^\s,]+(?:\s+[^\s,]+)*)', 'model': r'Model:\s*([^\s,]+)', 'cfg_scale': r'CFG scale:\s*([\d\.]+)', 'size': r'Size:\s*([0-9]+x[0-9]+)' } for key in ['prompt', 'negative_prompt', 'steps', 'seed', 'sampler', 'model', 'cfg_scale', 'size']: match = re.search(patterns[key], text) if match: results[key] = match.group(1) else: results[key] = None if results['size'] is not None: w, h = results['size'].split("x") results['w'] = w results['h'] = h else: results['w'] = None results['h'] = None return results def send_to_txt2img(image): result = {tabs: gr.Tabs.update(selected="t2i")} try: text = image.info['parameters'] data = get_data(text) result[prompt] = gr.update(value=data['prompt']) result[negative_prompt] = gr.update(value=data['negative_prompt']) if data[ 'negative_prompt'] is not None else gr.update() result[steps] = gr.update(value=int(data['steps'])) if data['steps'] is not None else gr.update() result[seed] = gr.update(value=int(data['seed'])) if data['seed'] is not None else gr.update() result[cfg_scale] = gr.update(value=float(data['cfg_scale'])) if data['cfg_scale'] is not None else gr.update() result[width] = gr.update(value=int(data['w'])) if data['w'] is not None else gr.update() result[height] = gr.update(value=int(data['h'])) if data['h'] is not None else gr.update() result[sampler] = gr.update(value=data['sampler']) if data['sampler'] is not None else gr.update() if data['model'] in model_names: result[model] = gr.update(value=model_names[data['model']]) else: result[model] = gr.update() return result except Exception as e: print(e) result[prompt] = gr.update() result[negative_prompt] = gr.update() result[steps] = gr.update() result[seed] = gr.update() result[cfg_scale] = gr.update() result[width] = gr.update() result[height] = gr.update() result[sampler] = gr.update() result[model] = gr.update() return result def place_lora(current_prompt, lora_name): pattern = r"" if re.search(pattern, current_prompt): yield re.sub(pattern, "", current_prompt) else: yield current_prompt + " " prodia_client = Prodia(api_key=os.getenv("PRODIA_API_KEY")) model_list = prodia_client.list_models() lora_list = prodia_client.list_loras() model_names = {} for model_name in model_list: name_without_ext = remove_id_and_ext(model_name) model_names[name_without_ext] = model_name def txt2img(prompt, negative_prompt, model, steps, sampler, cfg_scale, width, height, seed, batch_count, gallery): yield { text_button: gr.update(visible=False), stop_btn: gr.update(visible=True), } data = { "prompt": prompt, "negative_prompt": negative_prompt, "model": model, "steps": steps, "sampler": sampler, "cfg_scale": cfg_scale, "width": width, "height": height, "seed": seed } total_images = [] threads = [] def generate_one_image(): result = prodia_client.generate(data) job = prodia_client.wait(result) total_images.append(job['imageUrl']) for x in range(batch_count): t = Thread(target=generate_one_image) threads.append(t) t.start() for t in threads: t.join() new_images_list = [img['name'] for img in gallery] for image in total_images: new_images_list.insert(0, image) if batch_count > 1: results = gr.update(value=total_images, preview=False) else: results = gr.update(value=total_images, preview=True) yield { text_button: gr.update(visible=True), stop_btn: gr.update(visible=False), image_output: results, gallery_obj: gr.update(value=new_images_list), } def img2img(input_image, denoising, prompt, negative_prompt, model, steps, sampler, cfg_scale, width, height, seed, batch_count, gallery): if input_image is None: return yield { i2i_text_button: gr.update(visible=False), i2i_stop_btn: gr.update(visible=True), } data = { "imageData": image_to_base64(input_image), "denoising_strength": denoising, "prompt": prompt, "negative_prompt": negative_prompt, "model": model, "steps": steps, "sampler": sampler, "cfg_scale": cfg_scale, "width": width, "height": height, "seed": seed } total_images = [] threads = [] def generate_one_image(): result = prodia_client.transform(data) job = prodia_client.wait(result) total_images.append(job['imageUrl']) for x in range(batch_count): t = Thread(target=generate_one_image) threads.append(t) t.start() for t in threads: t.join() new_images_list = [img['name'] for img in gallery] for image in total_images: new_images_list.insert(0, image) if batch_count > 1: results = gr.update(value=total_images, preview=False) else: results = gr.update(value=total_images, preview=True) yield { i2i_text_button: gr.update(visible=True), i2i_stop_btn: gr.update(visible=False), i2i_image_output: results, gallery_obj: gr.update(value=new_images_list), } def upscale_fn(image, scale): if image is None: return yield { upscale_btn: gr.update(visible=False), upscale_stop: gr.update(visible=True), } job = prodia_client.upscale({ 'imageData': image_to_base64(image), 'resize': scale }) result = prodia_client.wait(job) yield { upscale_output: result['imageUrl'], upscale_btn: gr.update(visible=True), upscale_stop: gr.update(visible=False) } def stop_upscale(): return { upscale_btn: gr.update(visible=True), upscale_stop: gr.update(visible=False) } def stop_t2i(): return { text_button: gr.update(visible=True), stop_btn: gr.update(visible=False) } def stop_i2i(): return { i2i_text_button: gr.update(visible=True), i2i_stop_btn: gr.update(visible=False) } samplers = [ "Euler", "Euler a", "LMS", "Heun", "DPM2", "DPM2 a", "DPM++ 2S a", "DPM++ 2M", "DPM++ SDE", "DPM fast", "DPM adaptive", "LMS Karras", "DPM2 Karras", "DPM2 a Karras", "DPM++ 2S a Karras", "DPM++ 2M Karras", "DPM++ SDE Karras", "DDIM", "PLMS", ] css = """ :root, .dark{ --checkbox-label-gap: 0.25em 0.1em; --section-header-text-size: 12pt; --block-background-fill: transparent; } .block.padded:not(.gradio-accordion) { padding: 0 !important; } div.gradio-container{ max-width: unset !important; } .compact{ background: transparent !important; padding: 0 !important; } div.form{ border-width: 0; box-shadow: none; background: transparent; overflow: visible; gap: 0.5em; } .block.gradio-dropdown, .block.gradio-slider, .block.gradio-checkbox, .block.gradio-textbox, .block.gradio-radio, .block.gradio-checkboxgroup, .block.gradio-number, .block.gradio-colorpicker { border-width: 0 !important; box-shadow: none !important; } .gradio-dropdown label span:not(.has-info), .gradio-textbox label span:not(.has-info), .gradio-number label span:not(.has-info) { margin-bottom: 0; } .gradio-dropdown ul.options{ z-index: 3000; min-width: fit-content; max-width: inherit; white-space: nowrap; } .gradio-dropdown ul.options li.item { padding: 0.05em 0; } .gradio-dropdown ul.options li.item.selected { background-color: var(--neutral-100); } .dark .gradio-dropdown ul.options li.item.selected { background-color: var(--neutral-900); } .gradio-dropdown div.wrap.wrap.wrap.wrap{ box-shadow: 0 1px 2px 0 rgba(0, 0, 0, 0.05); } .gradio-dropdown:not(.multiselect) .wrap-inner.wrap-inner.wrap-inner{ flex-wrap: unset; } .gradio-dropdown .single-select{ white-space: nowrap; overflow: hidden; } .gradio-dropdown .token-remove.remove-all.remove-all{ display: none; } .gradio-dropdown.multiselect .token-remove.remove-all.remove-all{ display: flex; } .gradio-slider input[type="number"]{ width: 6em; } .block.gradio-checkbox { margin: 0.75em 1.5em 0 0; } .gradio-html div.wrap{ height: 100%; } div.gradio-html.min{ min-height: 0; } #model_dd { width: 16%; } """ with gr.Blocks(css=css) as demo: model = gr.Dropdown(interactive=True, value="absolutereality_v181.safetensors [3d9d4d2b]", show_label=True, label="Stable Diffusion Checkpoint", choices=prodia_client.list_models(), elem_id="model_dd") with gr.Tabs() as tabs: with gr.Tab("txt2img", id='t2i'): with gr.Row(): with gr.Column(scale=6, min_width=600): prompt = gr.Textbox("space warrior, beautiful, female, ultrarealistic, soft lighting, 8k", placeholder="Prompt", show_label=False, lines=3) negative_prompt = gr.Textbox(placeholder="Negative Prompt", show_label=False, lines=3, value="3d, cartoon, anime, (deformed eyes, nose, ears, nose), bad anatomy, ugly") with gr.Row(): text_button = gr.Button("Generate", variant='primary', elem_id="generate") stop_btn = gr.Button("Cancel", variant="stop", elem_id="generate", visible=False) with gr.Row(): with gr.Column(): with gr.Tab("Generation"): with gr.Row(): with gr.Column(scale=1): sampler = gr.Dropdown(value="DPM++ 2M Karras", show_label=True, label="Sampling Method", choices=samplers) with gr.Column(scale=1): steps = gr.Slider(label="Sampling Steps", minimum=1, maximum=50, value=25, step=0.5) with gr.Row(): with gr.Column(scale=8): width = gr.Slider(label="Width", maximum=1024, value=512, step=8) height = gr.Slider(label="Height", maximum=1024, value=512, step=8) with gr.Column(scale=1): batch_size = gr.Slider(label="Batch Size", maximum=1, value=1) batch_count = gr.Slider(label="Batch Count", minimum=1, maximum=50, value=1, step=1) cfg_scale = gr.Slider(label="CFG Scale", minimum=1, maximum=20, value=7, step=1) seed = gr.Number(label="Seed", value=-1) with gr.Tab("Lora"): with gr.Row(): for lora in lora_list: lora_btn = gr.Button(lora, size="sm") lora_btn.click(place_lora, inputs=[prompt, lora_btn], outputs=prompt) with gr.Column(): image_output = gr.Gallery(columns=3, value=["https://images.prodia.xyz/8ede1a7c-c0ee-4ded-987d-6ffed35fc477.png"]) with gr.Tab("img2img", id='i2i'): with gr.Row(): with gr.Column(scale=6, min_width=600): i2i_prompt = gr.Textbox("space warrior, beautiful, female, ultrarealistic, soft lighting, 8k", placeholder="Prompt", show_label=False, lines=3) i2i_negative_prompt = gr.Textbox(placeholder="Negative Prompt", show_label=False, lines=3, value="3d, cartoon, anime, (deformed eyes, nose, ears, nose), bad anatomy, ugly") with gr.Row(): i2i_text_button = gr.Button("Generate", variant='primary', elem_id="generate") i2i_stop_btn = gr.Button("Cancel", variant="stop", elem_id="generate", visible=False) with gr.Row(): with gr.Column(scale=1): with gr.Tab("Generation"): i2i_image_input = gr.Image(type="pil") with gr.Row(): with gr.Column(scale=1): i2i_sampler = gr.Dropdown(value="DPM++ 2M Karras", show_label=True, label="Sampling Method", choices=samplers) with gr.Column(scale=1): i2i_steps = gr.Slider(label="Sampling Steps", minimum=1, maximum=50, value=25, step=0.5) with gr.Row(): with gr.Column(scale=6): i2i_width = gr.Slider(label="Width", maximum=1024, value=512, step=8) i2i_height = gr.Slider(label="Height", maximum=1024, value=512, step=8) with gr.Column(scale=1): i2i_batch_size = gr.Slider(label="Batch Size", maximum=1, value=1) i2i_batch_count = gr.Slider(label="Batch Count", minimum=1, maximum=50, value=1, step=1) i2i_cfg_scale = gr.Slider(label="CFG Scale", minimum=1, maximum=20, value=7, step=1) i2i_denoising = gr.Slider(label="Denoising Strength", minimum=0, maximum=1, value=0.7, step=0.1) i2i_seed = gr.Number(label="Seed", value=-1) with gr.Tab("Lora"): with gr.Row(): for lora in lora_list: lora_btn = gr.Button(lora, size="sm") lora_btn.click(place_lora, inputs=[i2i_prompt, lora_btn], outputs=i2i_prompt) with gr.Column(scale=1): i2i_image_output = gr.Gallery(columns=3, value=["https://images.prodia.xyz/8ede1a7c-c0ee-4ded-987d-6ffed35fc477.png"]) with gr.Tab("Extras"): with gr.Row(): with gr.Tab("Single Image"): with gr.Column(): upscale_image_input = gr.Image(type="pil") upscale_btn = gr.Button("Generate", variant="primary") upscale_stop = gr.Button("Stop", variant="stop", visible=False) with gr.Tab("Scale by"): scale_by = gr.Radio([2, 4], value=2, label="Resize") upscale_output = gr.Image() with gr.Tab("PNG Info"): def plaintext_to_html(text, classname=None): content = "
\n".join(html.escape(x) for x in text.split('\n')) return f"

{content}

" if classname else f"

{content}

" def get_exif_data(image): items = image.info info = '' for key, text in items.items(): info += f"""

{plaintext_to_html(str(key))}

{plaintext_to_html(str(text))}

""".strip() + "\n" if len(info) == 0: message = "Nothing found in the image." info = f"

{message}

" return info with gr.Row(): with gr.Column(): image_input = gr.Image(type="pil") with gr.Column(): exif_output = gr.HTML(label="EXIF Data") send_to_txt2img_btn = gr.Button("Send to txt2img") with gr.Tab("Gallery"): gallery_obj = gr.Gallery(height=1000, columns=6) t2i_event = text_button.click(txt2img, inputs=[prompt, negative_prompt, model, steps, sampler, cfg_scale, width, height, seed, batch_count, gallery_obj], outputs=[image_output, gallery_obj, text_button, stop_btn]) stop_btn.click(fn=stop_t2i, outputs=[text_button, stop_btn], cancels=[t2i_event]) image_input.upload(get_exif_data, inputs=[image_input], outputs=exif_output) send_to_txt2img_btn.click(send_to_txt2img, inputs=[image_input], outputs=[tabs, prompt, negative_prompt, steps, seed, model, sampler, width, height, cfg_scale]) i2i_event = i2i_text_button.click(img2img, inputs=[i2i_image_input, i2i_denoising, i2i_prompt, i2i_negative_prompt, model, i2i_steps, i2i_sampler, i2i_cfg_scale, i2i_width, i2i_height, i2i_seed, i2i_batch_count, gallery_obj], outputs=[i2i_image_output, gallery_obj, i2i_text_button, i2i_stop_btn]) i2i_stop_btn.click(fn=stop_i2i, outputs=[i2i_text_button, i2i_stop_btn], cancels=[i2i_event]) upscale_event = upscale_btn.click(fn=upscale_fn, inputs=[upscale_image_input, scale_by], outputs=[upscale_output, upscale_btn, upscale_stop]) upscale_stop.click(fn=stop_upscale, outputs=[upscale_btn, upscale_stop], cancels=[upscale_event]) demo.queue().launch(max_threads=256)