Update app.py

app.py

@@ -5,6 +5,18 @@ from huggingface_hub import hf_hub_download
 from safetensors.torch import load_file
 import spaces
 
+
+def save_image(img):
+    unique_name = str(uuid.uuid4()) + ".png"
+    img.save(unique_name)
+    return unique_name
+
+def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+    return seed
+
+MAX_SEED = np.iinfo(np.int32).max
 vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
 
 ### RealVisXL V3 ###
@@ -75,16 +87,85 @@ pipe_hyper.to("cuda")
 del unet
 
 @spaces.GPU
-def run_comparison(prompt, progress=gr.Progress(track_tqdm=True)):
-    image_turbo=pipe_turbo(prompt=prompt, num_inference_steps=1, guidance_scale=0).images[0]
+def run_comparison(prompt: str,
+    negative_prompt: str = "",
+    use_negative_prompt: bool = False,
+    num_inference_steps: int = 30,
+    num_images_per_prompt: int = 2,
+    seed: int = 0,
+    width: int = 1024,
+    height: int = 1024,
+    guidance_scale: float = 3,
+    randomize_seed: bool = False,
+    progress=gr.Progress(track_tqdm=True),
+):
+    seed = int(randomize_seed_fn(seed, randomize_seed))
+    if not use_negative_prompt:
+        negative_prompt = ""
+    image_turbo=pipe_turbo(prompt=prompt,
+        negative_prompt=negative_prompt,
+        width=width,
+        height=height,
+        guidance_scale=guidance_scale,
+        num_inference_steps=num_inference_steps,
+        num_images_per_prompt=num_images_per_prompt,
+        cross_attention_kwargs={"scale": 0.65},
+        output_type="pil",
+        ).images
+    image_paths = [save_image(img) for img in images]
+    return image_paths, seed
     yield image_turbo, None, None, None, None
-    image_lightning=pipe_lightning(prompt=prompt, num_inference_steps=1, guidance_scale=0).images[0]
+    image_lightning=pipe_lightning(prompt=prompt,
+        negative_prompt=negative_prompt,
+        width=width,
+        height=height,
+        guidance_scale=guidance_scale,
+        num_inference_steps=num_inference_steps,
+        num_images_per_prompt=num_images_per_prompt,
+        cross_attention_kwargs={"scale": 0.65},
+        output_type="pil",
+        ).images
+    image_paths = [save_image(img) for img in images]
+    return image_paths, seed
     yield image_turbo, image_lightning, None, None, None
-    image_hyper=pipe_hyper(prompt=prompt, num_inference_steps=1, guidance_scale=0, timesteps=[800]).images[0]
+    image_hyper=pipe_hyper(prompt=prompt,
+        negative_prompt=negative_prompt,
+        width=width,
+        height=height,
+        guidance_scale=guidance_scale,
+        num_inference_steps=num_inference_steps,
+        num_images_per_prompt=num_images_per_prompt,
+        cross_attention_kwargs={"scale": 0.65},
+        output_type="pil",
+        ).images
+    image_paths = [save_image(img) for img in images]
+    return image_paths, seed
     yield image_turbo, image_lightning, image_hyper, None, None
-    image_r3=RealVisXLv3_pipe(prompt=prompt, num_inference_steps=8, guidance_scale=0).images[0]
+    image_r3=RealVisXLv3_pipe(prompt=prompt,
+        negative_prompt=negative_prompt,
+        width=width,
+        height=height,
+        guidance_scale=guidance_scale,
+        num_inference_steps=num_inference_steps,
+        num_images_per_prompt=num_images_per_prompt,
+        cross_attention_kwargs={"scale": 0.65},
+        output_type="pil",
+        ).images
+    image_paths = [save_image(img) for img in images]
+    return image_paths, seed
     yield image_turbo, image_lightning, image_hyper,image_r3, None
-    image_r4=RealVisXLv4_pipe(prompt=prompt, num_inference_steps=8, guidance_scale=0).images[0]
+    image_r4=RealVisXLv4_pipe(prompt=prompt,
+        negative_prompt=negative_prompt,
+        width=width,
+        height=height,
+        guidance_scale=guidance_scale,
+        num_inference_steps=num_inference_steps,
+        num_images_per_prompt=num_images_per_prompt,
+        cross_attention_kwargs={"scale": 0.65},
+        output_type="pil",
+        ).images
+    image_paths = [save_image(img) for img in images]
+    return image_paths, seed
     yield image_turbo, image_lightning, image_hyper,image_r3, image_r4
 
 examples = ["A dignified beaver wearing glasses, a vest, and colorful neck tie.",
@@ -100,6 +181,7 @@ with gr.Blocks() as demo:
     gr.Markdown("## One step SDXL comparison 🦶")
     gr.Markdown('Compare SDXL variants and distillations able to generate images in a single diffusion step')
     prompt = gr.Textbox(label="Prompt")
+    run = gr.Button("Run")
     with gr.Accordion("Advanced options", open=False):
         use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=True)
         negative_prompt = gr.Text(
@@ -159,35 +241,56 @@ with gr.Blocks() as demo:
                 value=6,
             )
 
-    run = gr.Button("Run")
     with gr.Row():
         with gr.Column():
-            image_turbo = gr.Image(label="SDXL Turbo")
+            image_turbo = gr.Gallery(label="SDXL Turbo",columns=1, preview=True,)
             gr.Markdown("## [SDXL Turbo](https://huggingface.co/stabilityai/sdxl-turbo)")
         with gr.Column():
-            image_lightning = gr.Image(label="SDXL Lightning")
+            image_lightning = gr.Gallery(label="SDXL Lightning",columns=1, preview=True,)
             gr.Markdown("## [SDXL Lightning](https://huggingface.co/ByteDance/SDXL-Lightning)")
         with gr.Column():
-            image_hyper = gr.Image(label="Hyper SDXL")
+            image_hyper = gr.Gallery(label="Hyper SDXL",columns=1, preview=True,)
             gr.Markdown("## [Hyper SDXL](https://huggingface.co/ByteDance/Hyper-SD)")
         with gr.Column():
-            image_r3 = gr.Image(label="RealVisXL V3")
+            image_r3 = gr.Gallery(label="RealVisXL V3",columns=1, preview=True,)
             gr.Markdown("## [RealVisXL V3](https://huggingface.co)")
         with gr.Column():
-            image_r4 = gr.Image(label="RealVisXL V4")
+            image_r4 = gr.Gallery(label="RealVisXL V4",columns=1, preview=True,)
             gr.Markdown("## [RealVisXL V3](https://huggingface.co)")
     image_outputs = [image_turbo, image_lightning, image_hyper, image_r3, image_r4]
     gr.on(
-        triggers=[prompt.submit, run.click],
+        triggers=[
+            prompt.submit,
+            negative_prompt.submit,
+            run_button.click,
+        ],
         fn=run_comparison,
-        inputs=prompt,
-        outputs=image_outputs
+        inputs=[
+            prompt,
+            negative_prompt,
+            use_negative_prompt,
+            num_inference_steps,
+            num_images_per_prompt,
+            seed,
+            width,
+            height,
+            guidance_scale,
+            randomize_seed,
+        ],
+        outputs=[image_outputs, seed],
+        api_name="run",
+    )
+    use_negative_prompt.change(
+        fn=lambda x: gr.update(visible=x),
+        inputs=use_negative_prompt,
+        outputs=negative_prompt,
+        api_name=False,
     )
     gr.Examples(
         examples=examples,
         fn=run_comparison,
         inputs=prompt,
-        outputs=image_outputs,
+        outputs=[image_outputs, seed],
         cache_examples=False,
         run_on_click=True
     )