Update README with some explanations and links.

README.md

@@ -5,12 +5,32 @@ language:
 
 ## DALL·E mini - Generate images from text
 
-Model generating images from a text prompt.
+### Model Description
 
-Outputs need to be decoded with [flax-community/vqgan_f16_16384](https://huggingface.co/flax-community/vqgan_f16_16384).
+This is an attempt to replicate OpenAI's [DALL·E](https://openai.com/blog/dall-e/), a model capable of generating arbitrary images from a text prompt that describes the desired result. 
 
-Model definition is currently in the [Github repo](https://github.com/borisdayma/dalle-mini) as `CustomFlaxBartForConditionalGeneration`.
+This model's architecture is a simplification of the original, and leverages previous open source efforts and available pre-trained models. Results have lower quality than OpenAI's, but the model can be trained and used on less demanding hardware. Our training was performed on a single TPU v3-8 for a few days.
 
-For more details on the model, refer to [the report](https://wandb.ai/dalle-mini/dalle-mini/reports/DALL-E-mini--Vmlldzo4NjIxODA).
+### Components of the Architecture
 
-For testing the model, refer to [the demo](https://huggingface.co/spaces/flax-community/dalle-mini).
+The system relies in the Flax/JAX infrastructure, which are ideal for TPU training. TPUs are not required, both Flax and JAX run very efficiently on GPU backends.
+
+The main components of the architecture include:
+
+* An encoder, based on [BART](https://arxiv.org/abs/1910.13461). The encoder's mission is to transform a sequence of input text tokens to a sequence of image tokens. The input tokens are extracted from the text prompt by using the model's tokenizer. The image tokens are a fixed-length sequence, and they represent indices in a VQGAN-based pre-trained codebook.
+
+* A decoder, with converts the image tokens to an image for visualization. As mentioned above, the decoder is based on a [VQGAN model](https://compvis.github.io/taming-transformers/).
+
+The model definition we use for the encoder can be downloaded from our [Github repo](https://github.com/borisdayma/dalle-mini). The encoder is reprensented by the class `CustomFlaxBartForConditionalGeneration`.
+
+To use the decoder, you need to follow the instructions in our accompanying VQGAN model in the hub, [flax-community/vqgan_f16_16384](https://huggingface.co/flax-community/vqgan_f16_16384).
+
+### How to Use
+
+The easiest way to get familiar with the code and the models is to follow the inference notebook we provide in our [github repo](https://github.com/borisdayma/dalle-mini/blob/main/dev/inference/inference_pipeline.ipynb). For your convenience, you can open it in Google Colaboratory: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/borisdayma/dalle-mini/blob/main/dev/inference/inference_pipeline.ipynb).
+
+If you just want to test the trained model and see what it comes up with, please visit [our demo](https://huggingface.co/spaces/flax-community/dalle-mini), available as a Space in huggingface's hub.
+
+### Additional Details
+
+Our [report](https://wandb.ai/dalle-mini/dalle-mini/reports/DALL-E-mini--Vmlldzo4NjIxODA) contains a lot of details about how the model was trained and shows many examples that demonstrate its capabilities.