Upload 3 files

app.py

@@ -0,0 +1,61 @@
+import streamlit as st
+from app_logic import text2image
+
+
+from io import BytesIO
+
+
+def app():
+    st.header("Text-to-image Web App")
+    st.subheader("Powered by Hugging Face")
+    user_input = st.text_area(
+        "Enter your text prompt below and click the button to submit."
+    )
+
+    option = st.selectbox(
+        "Select model (in order of processing time)",
+        (
+        "mukaist/DALLE-4K",    
+        "prithivMLmods/Canopus-Realism-LoRA",
+        "black-forest-labs/FLUX.1-dev",
+        "SG161222/RealVisXL_V4.0_Lightning",
+        "prompthero/openjourney",
+        "stabilityai/stable-diffusion-2-1",
+        "runwayml/stable-diffusion-v1-5",
+        "SG161222/RealVisXL_V3.0",
+        "CompVis/stable-diffusion-v1-4",
+        ),
+    )
+
+    with st.form("my_form"):
+        submit = st.form_submit_button(label="Submit text prompt")
+
+    if submit:
+        with st.spinner(text="Generating image ... It may take up to some time."):
+            im, start, end = text2image(prompt=user_input, repo_id=option)
+
+            buf = BytesIO()
+            im.save(buf, format="PNG")
+            byte_im = buf.getvalue()
+
+            hours, rem = divmod(end - start, 3600)
+            minutes, seconds = divmod(rem, 60)
+
+            st.success(
+                "Processing time: {:0>2}:{:0>2}:{:05.2f}.".format(
+                    int(hours), int(minutes), seconds
+                )
+            )
+
+            st.image(im)
+
+            st.download_button(
+                label="Click here to download",
+                data=byte_im,
+                file_name="generated_image.png",
+                mime="image/png",
+            )
+
+
+if __name__ == "__main__":
+    app()

app_logic.py

@@ -0,0 +1,84 @@
+from typing import Literal
+from diffusers import StableDiffusionPipeline
+import torch
+import time
+
+import os
+import io
+import requests
+from PIL import Image
+
+from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler
+#from huggingface_hub import hf_hub_download
+
+
+seed = 2024
+generator = torch.manual_seed(seed)
+
+NUM_ITERS_TO_RUN = 1
+NUM_INFERENCE_STEPS = 25
+NUM_IMAGES_PER_PROMPT = 1
+
+    
+# Add your hugging face hub token here.
+os.environ['HUGGINGFACEHUB_API_TOKEN'] = "Your_hub_API_KEY"
+
+def text2image(
+    prompt: str,
+    repo_id: Literal[
+        "prithivMLmods/Canopus-Realism-LoRA",
+        "black-forest-labs/FLUX.1-dev",
+        "SG161222/RealVisXL_V4.0_Lightning",
+        "prompthero/openjourney",
+        "stabilityai/stable-diffusion-2-1",
+        "runwayml/stable-diffusion-v1-5",
+        "SG161222/RealVisXL_V3.0",
+        "CompVis/stable-diffusion-v1-4",
+    ],
+):
+    start = time.time()
+
+    HF_TOKEN = os.getenv('HUGGINGFACEHUB_API_TOKEN')
+    API_URL = f"https://api-inference.huggingface.co/models/{repo_id}"
+    headers = {"Authorization": f"Bearer {HF_TOKEN}"}
+    payload = {"inputs":prompt}
+    response = requests.post(API_URL, headers=headers, json=payload)
+    image_bytes = response.content
+    image = Image.open(io.BytesIO(image_bytes))
+    upscaled_image = image.resize((2048,2048))
+
+    '''if torch.cuda.is_available():
+        print("Using GPU")
+        pipeline = StableDiffusionPipeline.from_pretrained(
+            repo_id,
+            torch_dtype=torch.float16,
+            use_safetensors=True,
+        ).to("cuda")
+
+        pipe = StableDiffusionXLPipeline.from_pretrained(
+            repo_id,
+            torch_dtype=torch.float16,
+            use_safetensors=True,
+        )
+        pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
+
+        pipe.load_lora_weights("prithivMLmods/Canopus-Realism-LoRA", weight_name="Canopus-Realism-LoRA.safetensors", adapter_name="rlms")
+        pipe.set_adapters("rlms")
+        pipe.to("cuda")
+    else:
+        print("Using CPU")
+        pipeline = StableDiffusionPipeline.from_pretrained(
+            repo_id,
+            torch_dtype=torch.float32,
+            use_safetensors=True,
+        )
+
+    for _ in range(NUM_ITERS_TO_RUN):
+        images = pipeline(
+            prompt,
+            num_inference_steps=NUM_INFERENCE_STEPS,
+            generator=generator,
+            num_images_per_prompt=NUM_IMAGES_PER_PROMPT,
+        ).images'''
+    end = time.time()
+    return upscaled_image, start, end

requirements.txt

@@ -0,0 +1,5 @@
+diffusers==0.30.0
+Pillow==10.4.0
+Requests==2.32.3
+streamlit==1.37.1
+torch==2.4.0+cu124