Add application files

app.py

@@ -0,0 +1,51 @@
+import gradio as gr
+
+def generate(prompt, n_prompt, modelName):
+    return models[modelName].process(prompt, n_prompt)
+
+def create_demo():
+    with gr.Blocks() as demo:
+        with gr.Column():
+            prompt = gr.Textbox(label='Prompt')
+            n_prompt = gr.Textbox( label='Negative Prompt', value= 'low res')
+            modelName = gr.Dropdown(choices = list(models.keys()), label = "Model", value=list(models.keys())[0])
+
+            run_button = gr.Button('Generar')
+
+        gr.Markdown("lunarnaut txt2img demo")
+        result = gr.Gallery(label='Output', show_label=False, elem_id='gallery').style(columns=1, rows=1, preview=True)
+
+        inputs = [
+            prompt,
+            n_prompt,
+            modelName,
+        ]
+
+        prompt.submit(
+            fn=generate,
+            inputs=inputs,
+            outputs=result
+        )
+        n_prompt.submit(
+            fn=generate,
+            inputs=inputs,
+            outputs=result
+        )
+
+        run_button.click(
+            fn=generate,
+            inputs=inputs,
+            outputs=result
+        )
+    return demo
+
+
+if __name__ == '__main__':
+    from model import Model
+    models = {
+        "Stable Diffusion v1.5": Model("runwayml/stable-diffusion-v1-5"),
+        "Anything v3.0": Model("Linaqruf/anything-v3.0"),
+        "Realistic Vision v2.0": Model("SG161222/Realistic_Vision_V2.0"),
+              }
+    demo = create_demo()
+    demo.queue().launch()

model.py

@@ -0,0 +1,48 @@
+from __future__ import annotations
+
+
+from diffusers import StableDiffusionPipeline, EulerDiscreteScheduler
+from diffusers import DPMSolverMultistepScheduler
+import torch
+import PIL.Image
+import numpy as np
+import datetime
+
+# Check environment
+print(f"Is CUDA available: {torch.cuda.is_available()}")
+print(f"CUDA device: {torch.cuda.get_device_name(torch.cuda.current_device())}")
+
+device = "cuda"
+
+class Model:
+    def __init__(self, modelID):
+
+        self.modelID = modelID
+        self.pipe = StableDiffusionPipeline.from_pretrained(modelID, torch_dtype=torch.float16)
+        self.pipe = self.pipe.to(device)
+        self.pipe.scheduler = DPMSolverMultistepScheduler.from_config(self.pipe.scheduler.config)
+        self.pipe.enable_xformers_memory_efficient_attention()
+
+    def process(self, 
+                prompt: str, 
+                negative_prompt: str,
+                guidance_scale:int = 7,
+                num_images:int = 1,
+                num_steps:int = 20,
+                ):
+        seed = np.random.randint(0, np.iinfo(np.int32).max)
+        generator = torch.Generator(device).manual_seed(seed)
+        now = datetime.datetime.now()
+        print(now)
+        print(self.modelID)
+        print(prompt)
+        print(negative_prompt)
+        with torch.inference_mode():
+            images = self.pipe(prompt=prompt,
+                         negative_prompt=negative_prompt,
+                         guidance_scale=guidance_scale,
+                         num_images_per_prompt=num_images,
+                         num_inference_steps=num_steps,
+                         generator=generator).images
+
+        return images

requirements.txt

@@ -0,0 +1,9 @@
+--extra-index-url https://download.pytorch.org/whl/cu113
+torch
+accelerate==0.18.0
+diffusers==0.16.0
+gradio==3.30.0
+safetensors==0.3.0
+torchvision==0.15.1
+transformers==4.28.1
+xformers==0.0.18