Update README.md

README.md

@@ -15,6 +15,31 @@ If you want to know how to use it once you've deployed it, please refer to this
 
 https://huggingface.co/jbilcke-hf/LTX-Video-for-InferenceEndpoints/blob/main/example.py
 
+## Why?
+
+## Setup on Hugging Face Inference Endpoints
+
+### Pick a large machine
+
+It is recommended to use at least a NVIDIA L40S with 48 Gb of VRAM.
+
+### Downloads all assets
+
+Make sure to select "Download everything" when selecting the model.
+
+Otherwise some files ending in `.pth` won't be downloaded.
+
+### Select Text-to-Video or Image-to-Video
+
+By default the handler will do Text-to-Video.
+
+To do Image-Text-To-Video, you need to set the environment variable `SUPPORT_INPUT_IMAGE_PROMPT` to a truish value (eg `True`).
+
+It is possible to support both pipelines at the same time of you modify the `handler.py`(I did that in the past).
+
+If you keep both pipelines active this will consume more memory.
+
+
 ## Credits
 
 For more information about this model, please see the [original HF repository here](https://huggingface.co/Lightricks/LTX-Video/).