Update README.md

README.md

@@ -28,8 +28,8 @@ language:
 - it
 - pt
 license: other
-license_name: ltx-2-open-weights-license
-license_link: https://static.lightricks.com/legal/ltx-2-open-weights-license-0.X.pdf
+license_name: ltx-2-community-license-agreement
+license_link: https://github.com/Lightricks/LTX-2/blob/main/LICENSE
 library_name: diffusers
 demo: https://app.ltx.studio/ltx-2-playground/i2v
 ---
@@ -39,7 +39,19 @@ This model card focuses on the LTX-2 model, codebase available [here](https://gi
 
 LTX-2 is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution. 
 
-<img src="./media/trailer.gif" alt="trailer" width="512">
+<div class="card-video">
+    <video
+        src="./assets/ltx-2-intro.mp4"
+        width="854"
+        height="480"
+        autoPlay
+        loop
+        playsInline
+        muted
+        controls
+    >
+    </video>
+</div>
 
 # Model Checkpoints
 
@@ -66,7 +78,7 @@ LTX-2 is accessible right away via the following links:
 # Run locally
 
 ## Direct use license
-You can use the models - full, distilled, upscalers and any derivatives of the models - for purposes under the [license](https://static.lightricks.com/legal/ltx-2-open-weights-license-0.X.pdf).
+You can use the models - full, distilled, upscalers and any derivatives of the models - for purposes under the [license](./LICENSE).
 
 ## ComfyUI
 We recommend you use the built-in LTXVideo nodes that can be found in the ComfyUI Manager. 
@@ -109,9 +121,8 @@ LTX-2 is supported in the [Diffusers Python library](https://huggingface.co/docs
 - The model may generate content that is inappropriate or offensive.
 - When generating audio without speech, the audio may be of lower quality.
 
-## Image-to-video examples
-| | | |
-|:---:|:---:|:---:|
-| ![example1](./media/ltx-video_i2v_example_00001.gif) | ![example2](./media/ltx-video_i2v_example_00002.gif) | ![example3](./media/ltx-video_i2v_example_00003.gif) |
-| ![example4](./media/ltx-video_i2v_example_00004.gif) | ![example5](./media/ltx-video_i2v_example_00005.gif) |  ![example6](./media/ltx-video_i2v_example_00006.gif) |
-| ![example7](./media/ltx-video_i2v_example_00007.gif) |  ![example8](./media/ltx-video_i2v_example_00008.gif) | ![example9](./media/ltx-video_i2v_example_00009.gif) |
+# Train the model
+
+The base (dev) model is fully trainable.
+It's extremely easy to reproduce the LoRAs and IC-LoRAs we publish with the model by following the instructions on the [LTX-2 Trainer Readme](https://github.com/Lightricks/LTX-2/blob/main/packages/ltx-trainer/README.md).
+Training for motion, style or likeness (sound+appearance) can take less than an hour in many settings.