-
Hi! Thank you for the great work!
I am trying to build a system that given an image, return k most similar images. I was trying to use laion/relaion2B-en-research from huggingface but decided to us…
-
-
When I download the laion-coco dataset via the url, about half of the downloads fail. Is this normal? Also, I want to know what download failure and resize failure mean
-
The LAION 100M dataset used for benchmarking has a large number of duplicate vectors, which is impacting the recall results of several test queries and making it impossible to achieve 0.99 recall. W…
-
Thanks you amazing work! we want to know you datasets about this laion-aesthetic-5plus download website or download ways, because we can't download in hugging face. If possible , can you provided you …
-
Hello Steven,
First of all, I would like to express my gratitude for your detailed tutorial. I use your train script but can not replicate the result.Here is the difference of my train details:
1. I…
-
我们试用了PPT模型，效果很赞！
我比较好奇LAION-aesthetic v2 5+这个数据集的大小。官网上说有300M image-text pairs。下载保存到硬盘上，大概有多大呢？
问这个问题，主要是想确认一下我们自己的服务器能不能放得下这个数据集。
期待作者的解答！
-
After downloading, I have a 100GB JSON file. How can I use it for training?
[root@VM-117-206 LAION-Glyph-1M]# ll -h
total 100G
-rw-r--r-- 1 root root 100G Aug 23 18:38 LAION-Glyph-1M.json
-
Dear developers,
I really appreciate your most most most valuable works. Could you please tell me how much data and training hours are utilized to distill the Flux into Flux Mini? This can help us …
-
We need to make sure `datachain pull` works on real user scenarios.
We also need to measure performance, i.e how much overhead we are bringing if user would do just plain export - import by himself.…