"""
This is NEW release of DreamDrop V2.0!
Features added:
1. Can generate up to 10 images at a time
2. Image Upscaler (x8) appeared
3. Integrated MagicPrompt (for Stable Diffusion and for Dall•E)
4. Added generation parameters menu (Steps, Samplers and CFG Sсale)
Enjoy!
"""
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 MagicPrompt import MagicPromptSD
from Upscaler import upscale_image
batch_count = 1
batch_size = 1
i2i_batch_count = 1
i2i_batch_size = 1
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 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}/sd/models")
return response.json()
def list_samplers(self):
response = self._get(f"{self.base}/sd/samplers")
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 model in model_names:
result[model] = gr.update(value=model_names[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
prodia_client = Prodia(api_key=os.environ.get("API_X_KEY")) # You can get the API key on https://docs.prodia.com/reference/getting-started-guide
model_list = prodia_client.list_models()
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, sampler, steps, cfg_scale, width, height, num_images):
generated_images = []
for _ in range(num_images):
result = prodia_client.generate({
"prompt": prompt,
"negative_prompt": negative_prompt,
"model": model,
"steps": steps,
"sampler": sampler,
"cfg_scale": cfg_scale,
"width": width,
"height": height,
"seed": -1
})
job = prodia_client.wait(result)
generated_images.append(job["imageUrl"])
return generated_images
def img2img(input_image, denoising, prompt, negative_prompt, model, sampler, steps, cfg_scale, i2i_width, i2i_height):
result = prodia_client.transform({
"imageData": image_to_base64(input_image),
"denoising_strength": denoising,
"prompt": prompt,
"negative_prompt": negative_prompt,
"model": i2i_model.value,
"steps": steps,
"sampler": sampler,
"cfg_scale": cfg_scale,
"width": i2i_width,
"height": i2i_height,
"seed": -1
})
job = prodia_client.wait(result)
return job["imageUrl"]
with gr.Blocks(css="style.css", theme="zenafey/prodia-web") as demo:
gr.Markdown("""
# 🥏 DreamDrop ```V2.0```
""")
with gr.Tabs() as tabs:
with gr.Tab("Text-to-Image", id='t2i'):
with gr.Row():
with gr.Column(scale=6, min_width=600):
prompt = gr.Textbox(label="Prompt", placeholder="a cute cat, 8k", lines=2)
negative_prompt = gr.Textbox(label="Negative Prompt", value="text, blurry, fuzziness", lines=1)
text_button = gr.Button("Generate", variant='primary')
with gr.Row():
with gr.Column(scale=5):
images_output = gr.Gallery(label="Result Image(s)", num_rows=1, num_cols=5, scale=1, allow_preview=True, preview=True)
with gr.Row():
with gr.Accordion("⚙️ Settings", open=False):
with gr.Column(scale=1):
model = gr.Dropdown(interactive=True, value="absolutereality_v181.safetensors [3d9d4d2b]",
show_label=True, label="Model",
choices=prodia_client.list_models())
with gr.Column(scale=1):
sampler = gr.Dropdown(label="Sampler", choices=prodia_client.list_samplers(), value="DPM++ SDE", interactive=True)
steps = gr.Slider(label="Steps", minimum=1, maximum=50, step=1, value=25, interactive=True)
cfg_scale = gr.Slider(label="CFG Scale", minimum=1, maximum=20, value=7, interactive=True)
width = gr.Slider(label="↔️ Width", maximum=1024, value=768, step=8)
height = gr.Slider(label="↕️ Height", maximum=1024, value=768, step=8)
num_images = gr.Slider(minimum=1, maximum=10, value=2, step=1, label="Image Count", interactive=True)
text_button.click(txt2img, inputs=[prompt, negative_prompt, model, sampler, steps, cfg_scale, width, height, num_images], outputs=images_output)
with gr.Tab("Image-to-Image", id='i2i'):
with gr.Row():
with gr.Column(scale=6):
with gr.Column(scale=1):
i2i_image_input = gr.Image(label="Input Image", type="pil", interactive=True)
with gr.Column(scale=6, min_width=600):
i2i_prompt = gr.Textbox(label="Prompt", placeholder="a cute cat, 8k", lines=2)
i2i_negative_prompt = gr.Textbox(label="Negative Prompt", lines=1, value="text, blurry, fuzziness")
with gr.Column():
i2i_text_button = gr.Button("Generate", variant='primary', elem_id="generate")
with gr.Column(scale=1):
i2i_image_output = gr.Image(label="Result Image(s)")
with gr.Row():
with gr.Accordion("⚙️ Settings", open=False):
with gr.Column(scale=1):
i2i_model = gr.Dropdown(interactive=True,
value="absolutereality_v181.safetensors [3d9d4d2b]",
show_label=True, label="Model",
choices=prodia_client.list_models())
with gr.Column(scale=1):
i2i_denoising = gr.Slider(label="Denoising Strength", minimum=0, maximum=1, value=0.7, step=0.1)
sampler = gr.Dropdown(label="Sampler", choices=prodia_client.list_samplers(), value="DPM++ SDE", interactive=True)
steps = gr.Slider(label="Steps", minimum=1, maximum=50, step=1, value=25, interactive=True)
cfg_scale = gr.Slider(label="CFG Scale", minimum=1, maximum=20, value=7, interactive=True)
i2i_width = gr.Slider(label="↔️ Width", maximum=1024, value=768, step=8)
i2i_height = gr.Slider(label="↕️ Height", maximum=1024, value=768, step=8)
i2i_text_button.click(img2img, inputs=[i2i_image_input, i2i_denoising, i2i_prompt, i2i_negative_prompt, model, sampler, steps, cfg_scale, i2i_width, i2i_height], outputs=i2i_image_output)
with gr.Tab("Upscaler"):
gr.Markdown("""
# Upscaler ```x8```
""")
radio_input = gr.Radio(label="Upscale Levels", choices=[2, 4, 6, 8], value=2)
gr.Interface(fn=upscale_image, inputs = [gr.Image(label="Input Image", interactive=True), radio_input], outputs = gr.Image(label="Upscaled 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))}
{message}