Update blocks/text2img.py

blocks/text2img.py

@@ -36,7 +36,7 @@ class StableDiffusionText2ImageGenerator:
         device = get_device()
         self.pipe = get_scheduler_list(pipe=self.pipe, scheduler=scheduler)
         self.pipe.to(device)
-        #self.pipe.enable_attention_slicing()
+        self.pipe.enable_attention_slicing()
 
         return self.pipe
 
@@ -45,7 +45,6 @@ class StableDiffusionText2ImageGenerator:
         model_path: str,
         prompt: str,
         negative_prompt: str,
-        num_images_per_prompt: int,
         scheduler: str,
         guidance_scale: int,
         num_inference_step: int,
@@ -56,7 +55,7 @@ class StableDiffusionText2ImageGenerator:
         print("model_path", model_path)
         print("prompt", prompt)
         print("negative_prompt", negative_prompt)
-        print("num_images_per_prompt", num_images_per_prompt)
+        print("num_images_per_prompt", 1)
         print("scheduler", scheduler)
         print("guidance_scale", guidance_scale)
         print("num_inference_step", num_inference_step)
@@ -79,7 +78,7 @@ class StableDiffusionText2ImageGenerator:
             height=height,
             width=width,
             negative_prompt=negative_prompt,
-            num_images_per_prompt=num_images_per_prompt,
+            num_images_per_prompt=1,
             num_inference_steps=num_inference_step,
             guidance_scale=guidance_scale,
             generator=generator,
@@ -95,18 +94,18 @@ class StableDiffusionText2ImageGenerator:
                 with gr.Column():
                     text2image_prompt = gr.Textbox(
                         lines=1,
-                        placeholder="Prompt",
                         show_label=False,
                         elem_id="prompt-text-input",
-                        value=''
-                    )
+                        value='',
+                        placeholder="Prompt, keywords that describe your image"
+                        )
 
                     text2image_negative_prompt = gr.Textbox(
                         lines=1,
-                        placeholder="Negative Prompt",
                         show_label=False,
                         elem_id = "negative-prompt-text-input",
-                        value=''
+                        value='',
+                        placeholder="Negative Prompt, keywords that describe what you don't want in your image",
                     )
 
                     # add button for generating a prompt from the prompt
@@ -122,67 +121,66 @@ class StableDiffusionText2ImageGenerator:
                         lines=1,
                         placeholder="Generated Prompt",
                         show_label=False,
+                        info="Auto generated prompts for inspiration.",
+                    )
+
+                    text2image_model_path = gr.Dropdown(
+                        choices=list(TEXT2IMG_MODEL_LIST.keys()),
+                        value=list(TEXT2IMG_MODEL_LIST.keys())[0],
+                        label="Text2Image Model Selection",
+                        elem_id="model-dropdown",
+                        info="Select the model you want to use for text2image generation."
+                    )
+
+                    text2image_scheduler = gr.Dropdown(
+                        choices=SCHEDULER_LIST,
+                        value=SCHEDULER_LIST[0],
+                        label="Scheduler",
+                        elem_id="scheduler-dropdown",
+                        info="Scheduler list for models. Different schdulers result in different outputs."
                     )
-                    with gr.Row():
-                        with gr.Column():
-                            text2image_model_path = gr.Dropdown(
-                                choices=list(TEXT2IMG_MODEL_LIST.keys()),
-                                value=list(TEXT2IMG_MODEL_LIST.keys())[0],
-                                label="Text2Image Model Selection",
-                                elem_id="model-dropdown",
-                            )
-
-                            text2image_guidance_scale = gr.Slider(
-                                minimum=0.1,
-                                maximum=15,
-                                step=0.1,
-                                value=7.5,
-                                label="Guidance Scale",
-                                elem_id = "guidance-scale-slider"
-                            )
-
-                            text2image_num_inference_step = gr.Slider(
-                                minimum=1,
-                                maximum=100,
-                                step=1,
-                                value=50,
-                                label="Num Inference Step",
-                                elem_id = "num-inference-step-slider"
-                            )
-                            text2image_num_images_per_prompt = gr.Slider(
-                                minimum=1,
-                                maximum=30,
-                                step=1,
-                                value=1,
-                                label="Number Of Images",
-                            )
-                        with gr.Row():
-                            with gr.Column():
-
-                                text2image_scheduler = gr.Dropdown(
-                                    choices=SCHEDULER_LIST,
-                                    value=SCHEDULER_LIST[0],
-                                    label="Scheduler",
-                                    elem_id="scheduler-dropdown",
-                                )
-
-                                text2image_size = gr.Slider(
-                                    minimum=128,
-                                    maximum=1280,
-                                    step=32,
-                                    value=512,
-                                    label="Image Size",
-                                    elem_id="image-size-slider",
-                                )
-
-                                text2image_seed_generator = gr.Slider(
-                                    label="Seed(0 for random)",
-                                    minimum=0,
-                                    maximum=1000000,
-                                    value=0,
-                                    elem_id="seed-slider",
-                                )
-                    text2image_predict = gr.Button(value="Generator") 
+
+
+
+                    text2image_size = gr.Slider(
+                        minimum=128,
+                        maximum=1280,
+                        step=32,
+                        value=768,
+                        label="Image Size",
+                        elem_id="image-size-slider",
+                        info = "Image size determines the height and width of the generated image. Higher the value, better the quality however slower the computation."
+                    )
+                    text2image_seed_generator = gr.Slider(
+                        label="Seed(0 for random)",
+                        minimum=0,
+                        maximum=1000000,
+                        value=0,
+                        elem_id="seed-slider",
+                        info="Set the seed to a specific value to reproduce the results."
+                    )
+
+
+                    text2image_guidance_scale = gr.Slider(
+                        minimum=0.1,
+                        maximum=15,
+                        step=0.1,
+                        value=7.5,
+                        label="Guidance Scale",
+                        elem_id = "guidance-scale-slider",
+                        info = "Guidance scale determines how much the prompt will affect the image. Higher the value, more the effect."
+                    )
+
+                    text2image_num_inference_step = gr.Slider(
+                        minimum=1,
+                        maximum=100,
+                        step=1,
+                        value=50,
+                        label="Num Inference Step",
+                        elem_id = "num-inference-step-slider",
+                        info = "Number of inference step determines the quality of the image. Higher the number, better the quality."
+                    )
+                    text2image_predict = gr.Button(value="Generate image") 
 
                 with gr.Column():
                     output_image = gr.Gallery(
@@ -197,14 +195,27 @@ class StableDiffusionText2ImageGenerator:
                             loading_icon = gr.HTML(loading_icon_html)
                             share_button = gr.Button("Save artwork", elem_id="share-btn")
 
-            
+                    gr.HTML(
+                        """
+                        <div id="model-description-text2img">
+                            <h3>Text2Image Models</h3>
+                            <p>Text to image models will generate an image guided by the prompt that is provided</p>
+                            <p>A prompt should be specified with keywords that describe the image you want to generate.</p>
+                            <p>Negative prompt can be used to specify keywords that you don't want in your image such as "blood" or "violence".</p>
+                            <p>Example prompt: "A painting of a cat sitting on a chair, fantasy themed, starry background"</p>
+                            <hr>
+                            <p>Stable Diffusion 1.5 & 2.1: Default model for many tasks. </p>
+                            <p>OpenJourney v4: Generates fantasy themed images similar to the Midjourney model. </p>
+                            <p>Dreamlike Photoreal 1.0 & 2.0 is SD 1.5 that generates realistic images. </p>
+                        </div>
+                        """
+                    )
             text2image_predict.click(
                 fn=StableDiffusionText2ImageGenerator().generate_image,
                 inputs=[
                     text2image_model_path,
                     text2image_prompt,
                     text2image_negative_prompt,
-                    text2image_num_images_per_prompt,
                     text2image_scheduler,
                     text2image_guidance_scale,
                     text2image_num_inference_step,