Update app.py

app.py

@@ -1,7 +1,6 @@
 import gradio as gr
 import torch
 import os
-import spaces
 import uuid
 
 from diffusers import AnimateDiffPipeline, MotionAdapter, EulerDiscreteScheduler
@@ -10,6 +9,8 @@ from huggingface_hub import hf_hub_download
 from safetensors.torch import load_file
 from PIL import Image
 
+SECRET_TOKEN = os.getenv('SECRET_TOKEN', 'default_secret')
+
 # Constants
 bases = {
     "ToonYou": "frankjoshua/toonyou_beta6",
@@ -28,23 +29,16 @@ dtype = torch.float16
 pipe = AnimateDiffPipeline.from_pretrained(bases[base_loaded], torch_dtype=dtype).to(device)
 pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config, timestep_spacing="trailing", beta_schedule="linear")
 
-# Safety checkers
-from safety_checker import StableDiffusionSafetyChecker
-from transformers import CLIPFeatureExtractor
-
-safety_checker = StableDiffusionSafetyChecker.from_pretrained("CompVis/stable-diffusion-safety-checker").to(device)
-feature_extractor = CLIPFeatureExtractor.from_pretrained("openai/clip-vit-base-patch32")
+def generate_image(secret_token, prompt, base, motion, step):
+    if secret_token != SECRET_TOKEN:
+        raise gr.Error(
+            f'Invalid secret token. Please fork the original space if you want to use it for yourself.')
 
-def check_nsfw_images(images: list[Image.Image]) -> list[bool]:
-    safety_checker_input = feature_extractor(images, return_tensors="pt").to(device)
-    has_nsfw_concepts = safety_checker(images=[images], clip_input=safety_checker_input.pixel_values.to(device))
-    return has_nsfw_concepts
 
-def generate_image(prompt, base, motion, step, progress=gr.Progress()):
     global step_loaded
     global base_loaded
     global motion_loaded
-    print(prompt, base, step)
+    # print(prompt, base, step)
 
     if step_loaded != step:
         repo = "ByteDance/AnimateDiff-Lightning"
@@ -81,25 +75,40 @@ def generate_image(prompt, base, motion, step, progress=gr.Progress()):
         callback_steps=1
     )
 
-    # AiTube aims for real time, but we are loosing FPS if we perform this step
-    #has_nsfw_concepts = check_nsfw_images([output.frames[0][0]])
-    #if has_nsfw_concepts[0]:
-    #    gr.Warning("NSFW content detected.")
-    #    return None
-
     name = str(uuid.uuid4()).replace("-", "")
     path = f"/tmp/{name}.mp4"
     
     # I think we are looking time here too, converting to mp4 is too slow, we should return
     # the frames unencoded to the frontend renderer
     export_to_video(output.frames[0], path, fps=10)
+
+    # Read the content of the video file and encode it to base64
+    with open(path, "rb") as video_file:
+        video_base64 = base64.b64encode(video_file.read()).decode('utf-8')
+
+    # Prepend the appropriate data URI header with MIME type
+    video_data_uri = 'data:video/mp4;base64,' + video_base64
     
-    return path
+    # clean-up (otherwise there is always a risk of "ghosting", eg. someone seeing the previous generated video",
+    # of one of the steps go wrong)
+    os.remove(path)
+
+    return video_data_uri
 
 
 # Gradio Interface
 with gr.Blocks() as demo:
+    gr.HTML("""
+        <div style="z-index: 100; position: fixed; top: 0px; right: 0px; left: 0px; bottom: 0px; width: 100%; height: 100%; background: white; display: flex; align-items: center; justify-content: center; color: black;">
+        <div style="text-align: center; color: black;">
+        <p style="color: black;">This space is a REST API to programmatically generate MP4 videos for AiTube, the next generation video platform.</p>
+        <p style="color: black;">Interested in using it? Look no further than the <a href="https://huggingface.co/spaces/ByteDance/AnimateDiff-Lightning" target="_blank">original space</a>!</p>
+        </div>
+        </div>""")
+    
 
+    secret_token = gr.Text(label='Secret Token', max_lines=1)
+    
     with gr.Group():
         with gr.Row():
             prompt = gr.Textbox(
@@ -138,30 +147,17 @@ with gr.Blocks() as demo:
                     ('2-Step', 2),
                     ('4-Step', 4),
                     ('8-Step', 8)],
-                value=2,
+                value=4,
                 interactive=True
             )
-            submit = gr.Button(
-                scale=1,
-                variant='primary'
-            )
-    video = gr.Video(
-        label='AnimateDiff-Lightning',
-        autoplay=True,
-        height=512,
-        width=912,
-        elem_id="video_output"
-    )
+            submit = gr.Button()
+
+    output_video_base64 = gr.Text()
 
-    prompt.submit(
-        fn=generate_image,
-        inputs=[prompt, select_base, select_motion, select_step],
-        outputs=video,
-    )
     submit.click(
         fn=generate_image,
-        inputs=[prompt, select_base, select_motion, select_step],
-        outputs=video,
+        inputs=[secret_token, prompt, select_base, select_motion, select_step],
+        outputs=output_video_base64,
     )
 
-demo.queue().launch()
+app.queue(max_size=12).launch(show_api=True)