Spaces:
Running
Running
# TEXT 2 IMAGE PLAYGROUND Documentation | |
## Overview | |
TEXT 2 IMAGE PLAYGROUND is a Gradio-based web application designed to generate images from text prompts using advanced AI models. It offers various model options, customization parameters, and a user-friendly interface for an enhanced user experience. | |
## Features | |
- **Model Selection**: Choose from multiple AI models to generate images with different styles and qualities. | |
- **Custom Prompts**: Input text prompts to define the content and style of the generated images. | |
- **Negative Prompts**: Use negative prompts to avoid unwanted elements in the images. | |
- **Image Customization**: Adjust parameters like seed, width, height, guidance scale, and number of inference steps. | |
- **Random Seed Generation**: Enable random seed generation for varied outputs. | |
- **Image Gallery**: View a gallery of predefined images for inspiration. | |
## Interface | |
### Description | |
```markdown | |
## TEXT 2 IMAGE PLAYGROUND 🥠 | |
``` | |
### CSS | |
```css | |
.gradio-container { | |
max-width: 690px !important; | |
} | |
h1 { | |
text-align: center; | |
} | |
footer { | |
visibility: hidden; | |
} | |
``` | |
### JavaScript | |
```javascript | |
function refresh() { | |
const url = new URL(window.location); | |
if (url.searchParams.get('__theme') !== 'dark') { | |
url.searchParams.set('__theme', 'dark'); | |
window.location.href = url.href; | |
} | |
} | |
``` | |
### Examples | |
Predefined text prompts for quick testing: | |
- 3d image, cute girl, in the style of Pixar... | |
- Chocolate dripping from a donut against a yellow background... | |
- Illustration of A starry night camp in the mountains... | |
- Man in brown leather jacket posing for camera... | |
- Commercial photography, giant burger... | |
## Model Options | |
```python | |
MODEL_OPTIONS = { | |
"Realism : V4.0_Lightning🔥": "SG161222/RealVisXL_V4.0_Lightning", | |
"Detailed/SOTA : Mobius🚀": "Corcelio/mobius", | |
"Anime : Cagliostrolab🍺": "cagliostrolab/animagine-xl-3.1" | |
} | |
``` | |
## Configuration | |
Environment variables and configurations: | |
```python | |
MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "4096")) | |
USE_TORCH_COMPILE = os.getenv("USE_TORCH_COMPILE", "0") == "1" | |
ENABLE_CPU_OFFLOAD = os.getenv("ENABLE_CPU_OFFLOAD", "0") == "1" | |
BATCH_SIZE = int(os.getenv("BATCH_SIZE", "1")) | |
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") | |
``` | |
## Model Loading and Preparation | |
Function to load and prepare models: | |
```python | |
def load_and_prepare_model(model_id): | |
pipe = StableDiffusionXLPipeline.from_pretrained( | |
model_id, | |
torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32, | |
use_safetensors=True, | |
add_watermarker=False, | |
).to(device) | |
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config) | |
if USE_TORCH_COMPILE: | |
pipe.compile() | |
if ENABLE_CPU_OFFLOAD: | |
pipe.enable_model_cpu_offload() | |
return pipe | |
models = {key: load_and_prepare_model(value) for key, value in MODEL_OPTIONS.items()} | |
``` | |
## Image Generation | |
Function to generate images based on user inputs: | |
```python | |
@spaces.GPU(duration=60, enable_queue=True) | |
def generate( | |
model_choice: str, | |
prompt: str, | |
negative_prompt: str = "", | |
use_negative_prompt: bool = False, | |
seed: int = 1, | |
width: int = 1024, | |
height: int = 1024, | |
guidance_scale: float = 3, | |
num_inference_steps: int = 25, | |
randomize_seed: bool = False, | |
use_resolution_binning: bool = True, | |
num_images: int = 1, | |
progress=gr.Progress(track_tqdm=True), | |
): | |
global models | |
pipe = models[model_choice] | |
seed = int(randomize_seed_fn(seed, randomize_seed)) | |
generator = torch.Generator(device=device).manual_seed(seed) | |
options = { | |
"prompt": [prompt] * num_images, | |
"negative_prompt": [negative_prompt] * num_images if use_negative_prompt else None, | |
"width": width, | |
"height": height, | |
"guidance_scale": guidance_scale, | |
"num_inference_steps": num_inference_steps, | |
"generator": generator, | |
"output_type": "pil", | |
} | |
if use_resolution_binning: | |
options["use_resolution_binning"] = True | |
images = [] | |
for i in range(0, num_images, BATCH_SIZE): | |
batch_options = options.copy() | |
batch_options["prompt"] = options["prompt"][i:i+BATCH_SIZE] | |
if "negative_prompt" in batch_options: | |
batch_options["negative_prompt"] = options["negative_prompt"][i:i+BATCH_SIZE] | |
images.extend(pipe(**batch_options).images) | |
image_paths = [save_image(img) for img in images] | |
return image_paths, seed | |
``` | |
## Load Predefined Images | |
Function to load predefined images for the gallery: | |
```python | |
def load_predefined_images(): | |
predefined_images = [ | |
"assets/1.png", | |
"assets/2.png", | |
"assets/3.png", | |
"assets/4.png", | |
"assets/5.png", | |
"assets/6.png", | |
"assets/7.png", | |
"assets/8.png", | |
"assets/9.png", | |
"assets/10.png", | |
"assets/11.png", | |
"assets/12.png", | |
] | |
return predefined_images | |
``` | |
## Gradio Interface | |
Creating the Gradio interface: | |
```python | |
with gr.Blocks(css=css, theme="bethecloud/storj_theme", js=js_func) as demo: | |
gr.Markdown(DESCRIPTIONx) | |
with gr.Row(): | |
prompt = gr.Text( | |
label="Prompt", | |
show_label=False, | |
max_lines=1, | |
placeholder="Enter your prompt", | |
value="Chocolate dripping from a donut against a yellow background, in the style of brocore, hyper-realistic oil --ar 2:3 --q 2 --s 750 --v 5 --ar 2:3 --q 2 --s 750 --v 5", | |
container=False, | |
) | |
run_button = gr.Button("Run🚀", scale=0) | |
result = gr.Gallery(label="Result", columns=1, show_label=False) | |
with gr.Row(): | |
model_choice = gr.Dropdown( | |
label="Model Selection ☑️", | |
choices=list(MODEL_OPTIONS.keys()), | |
value="Realism : V4.0_Lightning🔥" | |
) | |
with gr.Accordion("Advanced options", open=True): | |
num_images = gr.Slider( | |
label="Number of Images", | |
minimum=1, | |
maximum=1, | |
step=1, | |
value=1, | |
) | |
with gr.Row(): | |
with gr.Column(scale=1): | |
use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=True) | |
negative_prompt = gr.Text( | |
label="Negative prompt", | |
max_lines=5, | |
lines=4, | |
placeholder="Enter a negative prompt", | |
value="(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", | |
visible=True, | |
) | |
seed = gr.Slider( | |
label="Seed", | |
minimum=0, | |
maximum=MAX_SEED, | |
step=1, | |
value=0, | |
) | |
randomize_seed = gr.Checkbox(label="Randomize seed", value=True) | |
with gr.Row(): | |
width = gr.Slider( | |
label="Width", | |
minimum=512, | |
maximum=MAX_IMAGE_SIZE, | |
step=64, | |
value=1024, | |
) | |
height = gr.Slider( | |
label="Height", | |
minimum=512, | |
maximum=MAX_IMAGE_SIZE, | |
step=64, | |
value=1024, | |
) | |
with gr.Row(): | |
guidance_scale = gr.Slider( | |
label="Guidance Scale", | |
minimum=0.1, | |
maximum=6, | |
step=0.1, | |
value=3.0, | |
) | |
num_inference_steps = gr.Slider( | |
label="Number of inference steps", | |
minimum=1, | |
maximum=35, | |
step=1, | |
value=20, | |
) | |
gr.Examples( | |
examples=examples, | |
inputs=prompt, | |
cache_examples=False | |
) | |
use_negative_prompt.change( | |
fn=lambda x: gr.update(visible=x), | |
inputs=use_negative_prompt, | |
outputs=negative_prompt, | |
api_name=False, | |
) | |
gr.on( | |
triggers=[ | |
prompt.submit, | |
negative_prompt.submit, | |
run_button.click, | |
], | |
fn=generate, | |
inputs=[ | |
model_choice, | |
prompt, | |
negative_prompt, | |
use_negative_prompt, | |
seed, | |
width, | |
height, | |
guidance_scale, | |
num_inference_steps, | |
randomize_seed, | |
num_images | |
], | |
outputs=[result, seed], | |
api_name="run", | |
) | |
with gr.Column(scale=3): | |
gr.Markdown("### Image Gallery") | |
predefined_gallery = gr.Gallery(label="Image Gallery", columns=4, show_label=False, value=load | |
_predefined_images()) | |
if __name__ == "__main__": | |
demo.queue(max_size=40).launch(show_api=False) | |
``` | |
## Running the Application | |
To run the application, simply execute the script. The interface will launch and be accessible via a web browser. | |
```sh | |
python app.py | |
``` |