There’s another effort to recreate DALL-E: DALL-E
There’s also an effort to get text-image pairs from Common Crawl there, currently at 100 million.
There’s another effort to recreate DALL-E: DALL-E
There’s also an effort to get text-image pairs from Common Crawl there, currently at 100 million.
With this, our currently released models is located here: GitHub - robvanvolt/DALLE-models: Here is a collection of checkpoints for DALLE-pytorch models, from where you can keep on training or start generating images.
Along with the inference colab.
Status
A lot of these tasks can be done in parallel!
We can coordinate on the discord.
Status
dropna
for non-existing images on both datasetspandas.read_json("metadata.jsonl", orient="records", lines=True)
text_clean
or description_clean
or any other logicpredict_with_generate=False
as we would need to define metrics (not obvious to find anything better than the loss here). When it runs we can just log some sample predictions decoded with the VQGAN.Thanks everybody!!!
Status
Congrats everybody for the great results we’re getting!
Status update
Demo
Report
Documentation
Ongoing runs
Status update
Runs
wandb/hf-flax-dalle-mini/model-4oh3u7ca:latest
wandb/hf-flax-dalle-mini/model-4oh3u7ca:latest
Demo
Repos
from ../dalle-mini/model import CustomFlaxBartForConditionalGeneration
)Writeup
Status update
Our report is ready and looks awesome! Possible improvements:
Demo
Repo
Status update
Demo almost ready (just need to upgrade streamlit with HF when possible)
Report almost ready (let’s have some final read and check links, etc)
Repo
In addition to my previous comments, see the evaluation form that has great ideas from Patrick on what we can improve!
Status update
Almost done
Demo
Report
Model cards
Repo
Status
Let’s plan next steps soon.
For those following and don’t know, the demo has already been released.
Feel free to join the Dall-E Discord server to help with this project!