This is an attempt to replicate OpenAI's
DALL·E
, a model capable of generating arbitrary images from a text prompt that describes the desired result.
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.
Components of the Architecture
The system relies on 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
. The encoder transforms 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, which converts the image tokens to image pixels. As mentioned above, the decoder is based on a
VQGAN model
.
The model definition we use for the encoder can be downloaded from our
Github repo
. The encoder is represented 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
.
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
. For your convenience, you can open it in Google Colaboratory:
If you just want to test the trained model and see what it comes up with, please visit
our demo
, available in 🤗 Spaces.
Additional Details
Our
report
contains more details about how the model was trained and shows many examples that demonstrate its capabilities.
Runs of flax-community dalle-mini on huggingface.co
74
Total runs
0
24-hour runs
2
3-day runs
-23
7-day runs
30
30-day runs
More Information About dalle-mini huggingface.co Model
dalle-mini huggingface.co
dalle-mini huggingface.co is an AI model on huggingface.co that provides dalle-mini's model effect (), which can be used instantly with this flax-community dalle-mini model. huggingface.co supports a free trial of the dalle-mini model, and also provides paid use of the dalle-mini. Support call dalle-mini model through api, including Node.js, Python, http.
dalle-mini huggingface.co is an online trial and call api platform, which integrates dalle-mini's modeling effects, including api services, and provides a free online trial of dalle-mini, you can try dalle-mini online for free by clicking the link below.
flax-community dalle-mini online free url in huggingface.co:
dalle-mini is an open source model from GitHub that offers a free installation service, and any user can find dalle-mini on GitHub to install. At the same time, huggingface.co provides the effect of dalle-mini install, users can directly use dalle-mini installed effect in huggingface.co for debugging and trial. It also supports api for free installation.