test

README.md

@@ -4,7 +4,7 @@ emoji: 🐠
 colorFrom: blue
 colorTo: gray
 sdk: gradio
-sdk_version: 5.4.0
+sdk_version: 3.35.2
 app_file: app.py
 pinned: false
 duplicated_from: fffiloni/zeroscope

app.py

@@ -1,59 +1,26 @@
 import gradio as gr
-import os
-from gradio_client import Client, handle_file
-import numpy as np 
-import tempfile
-import imageio
-
+from share_btn import community_icon_html, loading_icon_html, share_js
 import torch
 from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
+from diffusers.utils import export_to_video
 
 pipe = DiffusionPipeline.from_pretrained("cerspense/zeroscope_v2_576w", torch_dtype=torch.float16)
 pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
 pipe.enable_model_cpu_offload()
 
-hf_token = os.environ.get("HF_TOKEN")
-
-def get_caption(image_in):
-    kosmos2_client = Client("fffiloni/Kosmos-2-API", hf_token=hf_token)
-    kosmos2_result = kosmos2_client.predict(
-		image_input=handle_file(image_in),
-		text_input="Detailed",
-		api_name="/generate_predictions"
-    )
-    print(f"KOSMOS2 RETURNS: {kosmos2_result}")
-
-    data = kosmos2_result[1]
-
-    # Extract and combine tokens starting from the second element
-    sentence = ''.join(item['token'] for item in data[1:])
+caption = gr.load(name="spaces/fffiloni/CoCa-clone")
 
-    # Find the last occurrence of "."
-    #last_period_index = full_sentence.rfind('.')
+def create_image_caption(image_init):
+    cap = caption(image_init, "Nucleus sampling", 1.2, 0.5, 5, 20, fn_index=0)
+    print("cap: " + cap)
+    return cap
 
-    # Truncate the string up to the last period
-    #truncated_caption = full_sentence[:last_period_index + 1]
-
-    # print(truncated_caption)
-    #print(f"\n—\nIMAGE CAPTION: {truncated_caption}")
-    
-    return sentence
-
-def export_to_video(frames: np.ndarray, fps: int) -> str:
-    frames = np.clip((frames * 255), 0, 255).astype(np.uint8)
-    out_file = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False)
-    writer = imageio.get_writer(out_file.name, format="FFMPEG", fps=fps)
-    for frame in frames:
-        writer.append_data(frame)
-    writer.close()
-    return out_file.name
-
-def infer(image_init, progress=gr.Progress(track_tqdm=True)):
-    prompt = get_caption(image_init)
-    video_frames = pipe(prompt, num_inference_steps=40, height=320, width=576, num_frames=24).frames[0]
-    video_path = export_to_video(video_frames, 12)
+def infer(image_init):
+    prompt = create_image_caption(image_init)
+    video_frames = pipe(prompt, num_inference_steps=40, height=320, width=576, num_frames=24).frames
+    video_path = export_to_video(video_frames)
     print(video_path)
-    return prompt, video_path
+    return prompt, video_path, gr.Group.update(visible=True)
 
 css = """
 #col-container {max-width: 510px; margin-left: auto; margin-right: auto;}
@@ -135,18 +102,22 @@ with gr.Blocks(css=css) as demo:
             """
         )
 
-        image_init = gr.Image(label="Image Init", type="filepath", sources=["upload"], elem_id="image-init")
+        image_init = gr.Image(label="Image Init",type="filepath", source="upload", elem_id="image-init")
         #inference_steps = gr.Slider(label="Inference Steps", minimum=10, maximum=100, step=1, value=40, interactive=False)
         submit_btn = gr.Button("Submit")
-        coca_cap = gr.Textbox(label="Caption", placeholder="Kosmos-2 caption will be displayed here", elem_id="coca-cap-in")
+        coca_cap = gr.Textbox(label="Caption", placeholder="CoCa Caption will be displayed here", elem_id="coca-cap-in")
         video_result = gr.Video(label="Video Output", elem_id="video-output")
 
-    submit_btn.click(
-        fn=infer,
-        inputs=[image_init],
-        outputs=[coca_cap, video_result],
-        show_api=False
-    )
+        with gr.Group(elem_id="share-btn-container", visible=False) as share_group:
+            community_icon = gr.HTML(community_icon_html)
+            loading_icon = gr.HTML(loading_icon_html)
+            share_button = gr.Button("Share to community", elem_id="share-btn")
+
+    submit_btn.click(fn=infer,
+                    inputs=[image_init],
+                    outputs=[coca_cap, video_result, share_group])
+    
+    share_button.click(None, [], [], _js=share_js)
 
-demo.queue(max_size=12).launch(show_api=False)
+demo.queue(max_size=12).launch()
         

requirements.txt

@@ -1,9 +1,6 @@
-numpy==1.26.4
 diffusers
 transformers
 accelerate
 torch==2.0.1
 opencv-python
-imageio[ffmpeg]==2.34.1
-huggingface_hub==0.25.2