Update app.py

app.py

@@ -14,7 +14,6 @@ from gradio_imageslider import ImageSlider
 
 translator = Translator()
 HF_TOKEN = os.environ.get("HF_TOKEN")
-HF_TOKEN_UPSCALER = os.environ.get("HF_TOKEN_UPSCALER")
 MAX_SEED = np.iinfo(np.int32).max
 CSS = "footer { visibility: hidden; }"
 JS = "function () { gradioURL = window.location.href; if (!gradioURL.endsWith('?__theme=dark')) { window.location.replace(gradioURL + '?__theme=dark'); } }"
@@ -31,49 +30,21 @@ async def generate_image(prompt, model, lora_word, width, height, scales, steps,
     image = await client.text_to_image(prompt=text, height=height, width=width, guidance_scale=scales, num_inference_steps=steps, model=model)
     return image, seed
 
-def get_clarity_upscale(prompt, img_path, upscale_factor):
-    client = Client("jbilcke-hf/clarity-upscaler")
-    result = client.predict(
-        img_path,
-        prompt,
-        "",
-        upscale_factor,
-        1,
-        3,
-        3,
-        "16",
-        "16",
-        "epicrealism_naturalSinRC1VAE.safetensors [84d76a0328]",
-        "DPM++ 2M Karras",
-        1,
-        3,
-        True,
-        3,
-        "Hello!!",
-        "Hello!!",
-        api_name="/predict"
-    )
-    print(result)
-    return result
-
-async def gen(prompt, basemodel, width, height, scales, steps, seed, upscale_factor, process_upscale, lora_model, process_lora, upscaler_choice):
-    model = lora_model
+async def gen(prompt, basemodel, width, height, scales, steps, seed, upscale_factor, process_upscale, lora_model, process_lora):
+    model = enable_lora(lora_model, basemodel) if process_lora else basemodel
     image, seed = await generate_image(prompt, model, "", width, height, scales, steps, seed)
     image_path = "temp_image.png"
     image.save(image_path)
     
     if process_upscale:
-        if upscaler_choice == "FineGrain":
-            upscale_image = get_upscale_finegrain(prompt, image_path, upscale_factor)
-        elif upscaler_choice == "Upscaler Clarity":
-            upscale_image = get_clarity_upscale(prompt, image_path, upscale_factor)
+        upscale_image = get_upscale_finegrain(prompt, image_path, upscale_factor)
     else:
         upscale_image = image_path
     
     return [image_path, upscale_image]
 
 def get_upscale_finegrain(prompt, img_path, upscale_factor):
-    client = Client("finegrain/finegrain-image-enhancer", hf_token=HF_TOKEN_UPSCALER)
+    client = Client("finegrain/finegrain-image-enhancer", hf_token=HF_TOKEN)
     result = client.predict(input_image=handle_file(img_path), prompt=prompt, negative_prompt="", seed=42, upscale_factor=upscale_factor, controlnet_scale=0.6, controlnet_decay=1, condition_scale=6, tile_width=112, tile_height=144, denoise_strength=0.35, num_inference_steps=18, solver="DDIM", api_name="/process")
     return result[1]
 
@@ -94,10 +65,9 @@ with gr.Blocks(css=CSS, js=JS, theme="Nymbo/Nymbo_Theme") as demo:
                 prompt = gr.Textbox(label="Prompt")
                 basemodel_choice = gr.Dropdown(label="Base Model", choices=["black-forest-labs/FLUX.1-schnell", "black-forest-labs/FLUX.1-DEV"], value="black-forest-labs/FLUX.1-schnell")
                 lora_model_choice = gr.Dropdown(label="LORA Model", choices=["Shakker-Labs/FLUX.1-dev-LoRA-add-details", "XLabs-AI/flux-RealismLora"], value="XLabs-AI/flux-RealismLora")
-                process_lora = gr.Checkbox(label="Process LORA", value=False)
-                process_upscale = gr.Checkbox(label="Process Upscale", value=False)
-                upscale_factor = gr.Radio(label="UpScale Factor", choices=[2, 4, 8], value=2, scale=2)
-                upscaler_choice = gr.Radio(label="Upscaler", choices=["FineGrain", "Upscaler Clarity"], value="FineGrain")
+                process_lora = gr.Checkbox(label="Process LORA")
+                process_upscale = gr.Checkbox(label="Process Upscale")
+                upscale_factor = gr.Radio(label="UpScale Factor", choices=[2, 4, 8], value=2)
                 
                 with gr.Accordion(label="Advanced Options", open=False):
                     width = gr.Slider(label="Width", minimum=512, maximum=1280, step=8, value=512)
@@ -114,7 +84,7 @@ with gr.Blocks(css=CSS, js=JS, theme="Nymbo/Nymbo_Theme") as demo:
                     queue=False
                 ).then(
                     fn=gen,
-                    inputs=[prompt, basemodel_choice, width, height, scales, steps, seed, upscale_factor, process_upscale, lora_model_choice, process_lora, upscaler_choice],
+                    inputs=[prompt, basemodel_choice, width, height, scales, steps, seed, upscale_factor, process_upscale, lora_model_choice, process_lora],
                     outputs=[output_res]
                 )
 demo.launch()