Update app.py

app.py

@@ -12,144 +12,148 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 pipe = AutoPipelineForText2Image.from_pretrained("briaai/BRIA-2.3", torch_dtype=torch.float16, force_zeros_for_empty_prompt=False).to(device)
 pipe.load_ip_adapter("briaai/DEV-Image-Prompt", subfolder='models', weight_name="ip_adapter_bria.bin")
 
-default_negative_prompt= "" #"Logo,Watermark,Text,Ugly,Morbid,Extra fingers,Poorly drawn hands,Mutation,Blurry,Extra limbs,Gross proportions,Missing arms,Mutated hands,Long neck,Duplicate,Mutilated,Mutilated hands,Poorly drawn face,Deformed,Bad anatomy,Cloned face,Malformed limbs,Missing legs,Too many fingers"
+# default_negative_prompt= "" #"Logo,Watermark,Text,Ugly,Morbid,Extra fingers,Poorly drawn hands,Mutation,Blurry,Extra limbs,Gross proportions,Missing arms,Mutated hands,Long neck,Duplicate,Mutilated,Mutilated hands,Poorly drawn face,Deformed,Bad anatomy,Cloned face,Malformed limbs,Missing legs,Too many fingers"
 
+MAX_SEED = np.iinfo(np.int32).max
 
-def read_content(file_path: str) -> str:
-    """read the content of target file
-    """
-    with open(file_path, 'r', encoding='utf-8') as f:
-        content = f.read()
+@spaces.GPU
+def predict(prompt, ip_adapter_image, ip_adapter_scale=0.5, negative_prompt="", seed=100, randomize_seed=False, center_crop=False, width=1024, height=1024, guidance_scale=5.0, num_inference_steps=50, progress=gr.Progress(track_tqdm=True)):
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
 
-    return content
-
-def predict(image, prompt="high quality, best quality", negative_prompt="", guidance_scale=5, steps=30, ip_adapter_scale = 1.0, width=1024, height=1024, seed=0):
-
-    pipe.set_ip_adapter_scale(ip_adapter_scale)
-
-    if negative_prompt == "":
-        negative_prompt = None
+    if not center_crop:
+        ip_adapter_image.resize((224,224))
     
-    init_image = image['composite'].convert("RGB")    
-    # init_image = image.convert("RGB")
-    # if center_crop is False:
-    # init_image = init_image.resize((224, 224))
+    generator = torch.Generator(device="cuda").manual_seed(seed)
+    pipe.to("cuda")
+    image_encoder.to("cuda")
+    pipe.image_encoder = image_encoder
+    pipe.set_ip_adapter_scale([ip_adapter_scale])
     
-    generator = torch.Generator(device="cpu").manual_seed(int(seed))
-        
-    output = pipe(
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    ip_adapter_image=init_image,
-    num_inference_steps=int(steps),
-    generator=generator,
-    height=int(height), width=int(width),
-    guidance_scale=guidance_scale
-    )
-
-    torch.cuda.empty_cache
-    return output.images[0] #, gr.update(visible=True)
-
-
-css = '''
-.gradio-container{max-width: 1100px !important}
-#image_upload{min-height:400px}
-#image_upload [data-testid="image"], #image_upload [data-testid="image"] > div{min-height: 400px}
-#mask_radio .gr-form{background:transparent; border: none}
-#word_mask{margin-top: .75em !important}
-#word_mask textarea:disabled{opacity: 0.3}
-.footer {margin-bottom: 45px;margin-top: 35px;text-align: center;border-bottom: 1px solid #e5e5e5}
-.footer>p {font-size: .8rem; display: inline-block; padding: 0 10px;transform: translateY(10px);background: white}
-.dark .footer {border-color: #303030}
-.dark .footer>p {background: #0b0f19}
-.acknowledgments h4{margin: 1.25em 0 .25em 0;font-weight: bold;font-size: 115%}
-#image_upload .touch-none{display: flex}
-@keyframes spin {
-    from {
-        transform: rotate(0deg);
-    }
-    to {
-        transform: rotate(360deg);
-    }
+    image = pipe(
+        prompt=prompt,
+        ip_adapter_image=[ip_adapter_image],
+        negative_prompt=negative_prompt,
+        height=height,
+        width=width,
+        num_inference_steps=num_inference_steps,
+        guidance_scale=guidance_scale,
+        num_images_per_prompt=1,
+        generator=generator,
+    ).images[0]
+    
+    return image, seed
+
+examples = [
+    ["A dog", "minta.jpeg", 0.4],
+    ["A capybara", "king-min.png", 0.5],
+    ["A cat", "blue_hair.png", 0.5],
+    ["", "meow.jpeg", 1.0],
+]
+
+css="""
+#col-container {
+    margin: 0 auto;
+    max-width: 720px;
 }
-#share-btn-container {padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; max-width: 13rem; margin-left: auto;}
-div#share-btn-container > div {flex-direction: row;background: black;align-items: center}
-#share-btn-container:hover {background-color: #060606}
-#share-btn {all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.5rem !important; padding-bottom: 0.5rem !important;right:0;}
-#share-btn * {all: unset}
-#share-btn-container div:nth-child(-n+2){width: auto !important;min-height: 0px !important;}
-#share-btn-container .wrap {display: none !important}
-#share-btn-container.hidden {display: none!important}
-#prompt input{width: calc(100% - 160px);border-top-right-radius: 0px;border-bottom-right-radius: 0px;}
-#run_button{position:absolute;margin-top: 11px;right: 0;margin-right: 0.8em;border-bottom-left-radius: 0px;
-    border-top-left-radius: 0px;}
-#prompt-container{margin-top:-18px;}
-#prompt-container .form{border-top-left-radius: 0;border-top-right-radius: 0}
-#image_upload{border-bottom-left-radius: 0px;border-bottom-right-radius: 0px}
-'''
-
-image_blocks = gr.Blocks(css=css, elem_id="total-container")
-with image_blocks as demo:
+#result img{
+    object-position: top;
+}
+#result .image-container{
+    height: 100%
+}
+"""
+with gr.Blocks(css=css) as demo:
     with gr.Column(elem_id="col-container"):
-        gr.Markdown("## BRIA 2.3")
-        gr.HTML('''
-          <p style="margin-bottom: 10px; font-size: 94%">
-            This is a demo for 
-            <a href="https://huggingface.co/briaai/BRIA-2.3" target="_blank">BRIA 2.3 text-to-image </a>. 
-            BRIA 2.3 improve the generation of humans and illustrations compared to BRIA 2.2 while still trained on licensed data, and so provide full legal liability coverage for copyright and privacy infringement.
-          </p>
-        ''')
-    with gr.Row():
-                with gr.Column():
-                    # image = gr.ImageEditor(elem_id="image_upload", type="pil", label="Upload", height=400)
-                    image = gr.ImageEditor(type='pil', image_mode="RGB",  width=512, height=512, interactive=True, ) 
-
-                    # image = gr.Image(sources=None, type="pil") # None for upload, ctrl+v and webcam
-                    
-                    
-                    with gr.Row(elem_id="prompt-container", equal_height=True):
-                        with gr.Row():
-                            prompt = gr.Textbox(placeholder="Your prompt (you can leave it empty if you only want the image prompt as input)", show_label=False, elem_id="prompt")
-                            btn = gr.Button("Generate!", elem_id="run_button")
-
-                    with gr.Accordion(label="Settings", open=True):
-                        with gr.Row(equal_height=True):
-                            ip_adapter_scale = gr.Number(value=1.0, minimum=0.01, maximum=1.0, step=0.01, label="ip_adapter_scale")
-                            width = gr.Number(value=1024, minimum=300, maximum=2000, step=1, label="width")
-                            height = gr.Number(value=1024, minimum=300, maximum=2000, step=1, label="height")                    
-                    
-                    with gr.Accordion(label="Advanced Settings", open=False):
-                        with gr.Row(equal_height=True):
-                            guidance_scale = gr.Number(value=7, minimum=1.0, maximum=10.0, step=0.5, label="guidance_scale")
-                            steps = gr.Number(value=30, minimum=10, maximum=100, step=1, label="steps")
-                            seed = gr.Number(value=0, minimum=0, maximum=100000, step=1, label="seed")                                                        
-                            negative_prompt = gr.Textbox(label="negative_prompt", value=default_negative_prompt, placeholder=default_negative_prompt, info="what you don't want to see in the image")
-                            center_crop = gr.Checkbox(label="center_crop", info="If not checked, the image would be resized to square before it's fed to the model."),
-
-                        
-                with gr.Column():
-                    image_out = gr.Image(label="Output", elem_id="output-img", height=400)
-
+        gr.Markdown(f"""
+        # Kolors IP-Adapter - image reference and variations
+        """)
+        
+        with gr.Row():
+            prompt = gr.Text(
+                label="Prompt",
+                show_label=False,
+                max_lines=1,
+                placeholder="Enter your prompt",
+                container=False,
+            )
+            run_button = gr.Button("Run", scale=0)
+        
+        with gr.Row():
+            with gr.Column():
+                ip_adapter_image = gr.Image(label="IP-Adapter Image", type="pil")
+                ip_adapter_scale = gr.Slider(
+                    label="Image Input Scale",
+                    info="Use 1 for creating image variations",
+                    minimum=0.0,
+                    maximum=1.0,
+                    step=0.05,
+                    value=0.5,
+                )
+            result = gr.Image(label="Result", elem_id="result")
+
+        with gr.Accordion("Advanced Settings", open=False):
+            negative_prompt = gr.Text(
+                label="Negative prompt",
+                max_lines=1,
+                placeholder="Enter a negative prompt",
+            )
+            seed = gr.Slider(
+                label="Seed",
+                minimum=0,
+                maximum=MAX_SEED,
+                step=1,
+                value=0,
+            )
+            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+            center_crop = gr.Checkbox(label="Center Crop image", value=False, info="If not checked, the IP-Adapter image input would be resized to a square.")            
+            with gr.Row():
+                width = gr.Slider(
+                    label="Width",
+                    minimum=256,
+                    maximum=2048,
+                    step=32,
+                    value=1024,
+                )
+                height = gr.Slider(
+                    label="Height",
+                    minimum=256,
+                    maximum=2048,
+                    step=32,
+                    value=1024,
+                )
+            with gr.Row():
+                guidance_scale = gr.Slider(
+                    label="Guidance scale",
+                    minimum=0.0,
+                    maximum=10.0,
+                    step=0.1,
+                    value=5.0,
+                )
+                num_inference_steps = gr.Slider(
+                    label="Number of inference steps",
+                    minimum=1,
+                    maximum=100,
+                    step=1,
+                    value=25,
+                )
             
-
-    btn.click(fn=predict, inputs=[image, prompt, negative_prompt, guidance_scale, steps, ip_adapter_scale, width, height, seed], outputs=[image_out], api_name='run')
-    prompt.submit(fn=predict, inputs=[image, prompt, negative_prompt, guidance_scale, steps, ip_adapter_scale, width, height, seed], outputs=[image_out])
-
-    # gr.Examples(
-    #             examples=[
-    #                 ["./imgs/example.png"],
-    #             ],
-    #             fn=predict,
-    #             inputs=[image],
-    #             cache_examples=False,
-    # )
-    gr.HTML(
-        """
-            <div class="footer">
-                <p>Model by <a href="https://huggingface.co/diffusers" style="text-decoration: underline;" target="_blank">Diffusers</a> - Gradio Demo by 🤗 Hugging Face
-                </p>
-            </div>
-        """
+        
+        gr.Examples(
+            examples=examples,
+            fn=predict,
+            inputs=[prompt, ip_adapter_image, ip_adapter_scale],
+            outputs=[result, seed],
+            cache_examples="lazy"
+        )
+
+    gr.on(
+        triggers=[run_button.click, prompt.submit],
+        fn=predict,
+        inputs=[prompt, ip_adapter_image, ip_adapter_scale, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
+        outputs=[result, seed]
     )
 
-image_blocks.queue(max_size=25,api_open=False).launch(show_api=False)
+demo.queue(max_size=25,api_open=False).launch(show_api=False)
+
+# image_blocks.queue(max_size=25,api_open=False).launch(show_api=False)