import numpy as np import gradio as gr import requests import time import json import base64 import os from PIL import Image from io import BytesIO 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}/job", params) return response.json() def transform(self, params): response = self._post(f"{self.base}/transform", params) return response.json() def controlnet(self, params): response = self._post(f"{self.base}/controlnet", 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(0.25) job_result = self.get_job(job['job']) return job_result def list_models(self): response = self._get(f"{self.base}/models/list") 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_path): # Open the image with PIL with Image.open(image_path) as 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 prodia_client = Prodia(api_key=os.getenv("PRODIA_API_KEY")) def flip_text(prompt, negative_prompt, model, steps, sampler, cfg_scale): result = prodia_client.generate({ "prompt": prompt, "negative_prompt": negative_prompt, "model": model, "steps": steps, "sampler": sampler, "cfg_scale": cfg_scale }) job = prodia_client.wait(result) return job["imageUrl"] css = """ #generate { height: 100%; } """ with gr.Blocks(css=css) as demo: with gr.Tab("txt2img"): with gr.Row(): with gr.Column(scale=6, min_width=600): prompt = gr.Textbox(placeholder="Prompt", show_label=False, lines=3) negative_prompt = gr.Textbox(placeholder="Negative Prompt", show_label=False, lines=3) with gr.Column(equal_height=True): text_button = gr.Button("Generate", variant='primary', elem_id="generate") with gr.Row(): with gr.Column(scale=1): with gr.Tab("Generation"): with gr.Row(): with gr.Column(scale=1): model = gr.Dropdown(interactive=True,value="v1-5-pruned-emaonly.safetensors [d7049739]", show_label=False, choices=prodia_client.list_models()) sampler = gr.Dropdown(value="Euler a", show_label=False, choices=[ "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", ]) with gr.Column(scale=1): steps = gr.Slider(label="Steps", miniumum=1, maximum=50, value=25) cfg_scale = gr.Slider(label="CFG Scale", miniumum=1, maximum=20, value=7) with gr.Column(scale=1): image_output = gr.Image() text_button.click(flip_text, inputs=[prompt, negative_prompt, model, steps, sampler, cfg_scale], outputs=image_output) demo.launch()