Readme update 2024.6 (#63)

* updated readme * added image generation flow * added gif * minor updates * Update README.md Co-authored-by: Radwan Ibrahim <[email protected]> * review fixes --------- Co-authored-by: Radwan Ibrahim <[email protected]>
openvinotoolkit · Dec 18, 2024 · 64e0aab · 64e0aab
1 parent 09b3a00
commit 64e0aab
Show file tree

Hide file tree

Showing 12 changed files with 41 additions and 12 deletions.
diff --git a/README.md b/README.md
@@ -2,35 +2,34 @@
 
 # OpenVINO™ Test Drive
 
-[![codecov](https://codecov.io/gh/openvinotoolkit/openvino_testdrive/graph/badge.svg?token=DH98FAPH65)](https://codecov.io/gh/openvinotoolkit/openvino_testdrive)
-[![openvino](https://img.shields.io/badge/openvino-2024.4-blue)]()
+[![openvino](https://img.shields.io/badge/openvino-2024.6-blue)]()
 
 </div>
 
 Get started with OpenVINO™ Test Drive, an application that allows you to run generative AI and vision models trained by [Intel® Geti™](https://docs.geti.intel.com/) directly on your computer or edge device using [OpenVINO™ Runtime](https://github.com/openvinotoolkit/openvino).
 
 
 <p align="center">
-  <img src="./docs/readme.gif" width="600" alt="sample">
+  <img src="./docs/llm_model_chat.gif" width="600" alt="sample">
 </p>
 
 With use of OpenVINO™ Test Drive you can:
 + **Chat with LLMs** and evaluating model performance on your computer or edge device
-+ **Experiment with different text prompts** to generate images using Stable Diffusion and Stable DiffusionXL models (coming soon)
-+ **Transcribe speech from video** using Whisper models, including generation of timestamps (coming soon)
++ **Experiment with different text prompts** to generate images using Stable Diffusion and Stable DiffusionXL models
++ **Transcribe speech from video** using Whisper models, including generation of timestamps
 + **Run and visualize results of models** trained by Intel® Geti™ using single image inference or batch inference mode
 
 ## Installation
 
-Download the latest release from the [Releases repository](https://storage.openvinotoolkit.org/repositories/openvino_testdrive/packages/).
+Download the latest release from the [Releases repository](https://storage.openvinotoolkit.org/repositories/openvino_testdrive/).
 
 > [!NOTE]
 > To verify downloaded file integrity, you can generate a SHA-256 of the downloaded file and compare it to the SHA-256 from corresponding `.sha256` file published in Releases repository. 
 
 <details>
 <summary>Installation on Windows</summary>
 
-1. Downloading the zip archive [Releases repository](https://storage.openvinotoolkit.org/repositories/openvino_testdrive/packages/) `Windows` folder .
+1. Downloading the zip archive [Releases repository](https://storage.openvinotoolkit.org/repositories/openvino_testdrive/) `Windows` folder .
 
 <p align="left">
   <img src="./docs/win_inst.gif" width="500">
@@ -52,24 +51,54 @@ Upon starting the application, you can import a model using either Hugging Face
 
 ### Text generation and LLM performance evaluation
 
-1. Find a model on Hugging Face and import it
+1. Choose a model from predefined set of popular models or pick one from Hugging Face using `Import model` -> `Hugging Face` and import it.
 <p align="left">
   <img src="./docs/llm_import.gif" width="500">
 </p>
 
-2. Chat with LLMs via `Playground` tab.
+2. Pick imported LLM from `My models` section and chat with it using `Playground` tab. You can export LLM via `Export model` button.
 <p align="left">
   <img src="./docs/llm_model_chat.gif" width="500">
 </p>
 
-3. Use `Performance metrics` tab to get model performance metrics on your computer or edge device
+3. Use `Performance metrics` tab to get LLM performance metrics on your computer.
 <p align="left">
   <img src="./docs/metrics.gif" width="500">
 </p>
 
+
+### Transcribe speech from video
+
+1. Try Whisper for video transcription.
+<p align="left">
+  <img src="./docs/st_import.gif" width="500">
+</p>
+
+2. Pick imported speech-to-text LLM from `My models` section and upload video for transcription. It is also possible to search words in transcript or download it.
+
+<p align="left">
+  <img src="./docs/video.gif" width="500">
+</p>
+
+3. Use `Performance metrics` tab to get LLM performance metrics on your computer.
+
+### Image generation
+
+1. Choose an image generation LLM from predefined set of popular models or pick one from Hugging Face using `Import model` -> `Hugging Face` and import it.
+
+2. Pick imported LLM from `My models` section and chat with it to generate image. It is also possible to download generated image.
+
+<p align="left">
+  <img src="./docs/ig.gif" width="500">
+</p>
+
+3. Use `Performance metrics` tab to get LLM performance metrics on your computer.
+
+You can export LLM via `Export model` button.
+
 ### Images inference with models trained by Intel® Geti™
 
-1. Download deployment code for the model in OpenVINO format trained by Intel® Geti™. 
+1. Download code deployment for the model in OpenVINO format trained by Intel® Geti™. 
 
 <p align="left">
   <img src="./docs/geti_download.gif" width="500">
@@ -90,7 +119,7 @@ Upon starting the application, you can import a model using either Hugging Face
   <img src="./docs/geti_cv.gif" width="500">
 </p>
 
-4. For batch inference, use `Batch inference` tab and provide paths to folder with input images in a `Source folder` and specify `Destination folder` for output batch inference results. Click on `Start` to start batch inference.
+4. For batch inference, use `Batch inference` tab, provide paths to folder with input images in a `Source folder` and specify `Destination folder` for output batch inference results. Click on `Start` to start batch inference.
 
 <p align="left">
   <img src="./docs/geti_batch.gif" width="500">

diff --git a/docs/geti_batch.gif b/docs/geti_batch.gif
diff --git a/docs/geti_cv.gif b/docs/geti_cv.gif
diff --git a/docs/geti_download.gif b/docs/geti_download.gif
diff --git a/docs/geti_import.gif b/docs/geti_import.gif
diff --git a/docs/ig.gif b/docs/ig.gif
diff --git a/docs/llm_import.gif b/docs/llm_import.gif
diff --git a/docs/llm_model_chat.gif b/docs/llm_model_chat.gif
diff --git a/docs/metrics.gif b/docs/metrics.gif
diff --git a/docs/readme.gif b/docs/readme.gif
diff --git a/docs/st_import.gif b/docs/st_import.gif
diff --git a/docs/video.gif b/docs/video.gif