Upload folder using huggingface_hub

app.py

@@ -31,15 +31,14 @@ image_to_action_block = ModularPipelineBlocks.from_pretrained("dn6/matrix-game-i
 
 blocks.sub_blocks.insert("image_to_action", image_to_action_block, 0)
 
-pipe = MatrixGameWanModularPipeline(blocks, "diffusers-internal-dev/matrix-game-2-modular")
+pipe = MatrixGameWanModularPipeline(blocks, "diffusers/matrix-game-2-modular")
 pipe.load_components(trust_remote_code=True, device_map="cuda", torch_dtype={"default": torch.bfloat16, "vae": torch.float32})
 
-@spaces.GPU(300)
-def predict(image, prompt):
-    output = pipe(image=image, prompt=prompt, num_frames=141)
+@spaces.GPU(120)
+def predict(prompt):
+    output = pipe(image=None, prompt=prompt, num_frames=141)
     return export_to_video(output.values['videos'][0], "output.mp4")
 
-
 examples = []
 
 css = """
@@ -60,19 +59,19 @@ with gr.Blocks(css=css) as demo:
     with gr.Column(elem_id="col-container"):
         with gr.Row():
             with gr.Column():
-                input_images = gr.Gallery(label="Input Images",
+                input_images = gr.Image(label="Input Image",
                                           show_label=False,
                                           type="pil",
                                           interactive=True)
 
             with gr.Column():
-                result = gr.Gallery(label="Result", show_label=False, type="pil")
+                result = gr.Video(label="Result")
 
         with gr.Row():
             prompt = gr.Text(
                     label="Prompt",
                     show_label=False,
-                    placeholder="describe the edit instruction",
+                    placeholder="describe how you want to move in the image",
                     container=False,
             )
             run_button = gr.Button("Run!", variant="primary")
@@ -81,11 +80,9 @@ with gr.Blocks(css=css) as demo:
         triggers=[run_button.click, prompt.submit],
         fn=predict,
         inputs=[
-            input_images,
             prompt,
         ],
-        outputs=[result],  # Added use_output_btn to outputs
+        outputs=[result],
     )
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()

requirements.txt

@@ -1,6 +1,6 @@
 accelerate==1.10.1
 einops==0.8.1
-flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu12torch2.8cxx11abiTRUE-cp310-cp310-linux_x86_64.whl
+flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiTRUE-cp310-cp310-linux_x86_64.whl
 hf-transfer==0.1.9
 hf-xet==1.1.8
 huggingface-hub==0.34.4
@@ -8,8 +8,8 @@ imageio==2.37.0
 imageio-ffmpeg==0.6.0
 safetensors==0.6.2
 sentencepiece==0.2.1
-torch
+torch==2.7.0
 torchao==0.12.0
-torchvision
+torchvision==0.22.0
 transformers==4.55.4
 diffusers @ git+https://github.com/huggingface/diffusers.git