Initial commit

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,12 @@
+---
+title: Text to Video
+emoji: ⚡
+colorFrom: red
+colorTo: green
+sdk: gradio
+sdk_version: 3.27.0
+app_file: app.py
+pinned: false
+tags:
+- tool
+---

app.py

@@ -0,0 +1,4 @@
+from transformers.tools.base import launch_gradio_demo
+from text_to_image import TextToVideoTool
+
+launch_gradio_demo(TextToVideoTool)

requirements.txt

@@ -0,0 +1,4 @@
+transformers @ git+https://github.com/huggingface/transformers@test_composition
+diffusers
+accelerate
+torch

text_to_video.py

@@ -0,0 +1,49 @@
+import torch
+
+from transformers.tools.base import Tool, get_default_device
+from transformers.utils import is_accelerate_available, is_diffusers_available
+
+if is_diffusers_available():
+    from diffusers import DiffusionPipeline
+
+
+TEXT_TO_VIDEO_DESCRIPTION = (
+    "This is a tool that creates a video according to a text description. It takes an input named `prompt` which "
+    "contains the image description, as well as an optional input `seconds` which will be the duration of the video. "
+    "The default is of two seconds. The tool outputs a video object."
+)
+
+
+class TextToVideoTool(Tool):
+    default_checkpoint = "damo-vilab/text-to-video-ms-1.7b"
+    description = TEXT_TO_VIDEO_DESCRIPTION
+
+    def __init__(self, device=None, **hub_kwargs) -> None:
+        if not is_accelerate_available():
+            raise ImportError("Accelerate should be installed in order to use tools.")
+        if not is_diffusers_available():
+            raise ImportError("Diffusers should be installed in order to use the StableDiffusionTool.")
+
+        super().__init__()
+
+        self.device = device
+        self.pipeline = None
+        self.hub_kwargs = hub_kwargs
+
+    def setup(self):
+        if self.device is None:
+            self.device = get_default_device()
+
+        self.pipeline = DiffusionPipeline.from_pretrained(
+            self.default_checkpoint, torch_dtype=torch.float16, variant="fp16"
+        )
+        self.pipeline.to(self.device)
+
+        self.is_initialized = True
+
+    def __call__(self, prompt, seconds=2):
+        if not self.is_initialized:
+            self.setup()
+
+        return self.pipeline(prompt, num_frames=8 * seconds).frames
+

tool_config.json

@@ -0,0 +1,3 @@
+{
+  "custom_tools": {"text-to-video": "text_to_video.TextToVideoTool"}
+}