-
did anyone train on your own dataset and got good performance?
Hi, I wanna train on my own data but seems there is some dependence on datasets like "batch['__url__']" in train.py: https://github.…
-
When I try to finetune a 1step SDXL model with LoRA, I got an error:
Traceback (most recent call last):
File "main/train_sd.py", line 701, in
trainer.train()
File "main/train_sd.py", line…
-
For MindEye we mapped to CLIP ViT-L/32 final layer (shape 1x768) as well as to CLIP ViT-L/32 last hidden layer (shape 257x768). For the former we found that using a pretrained starting point for fine-…
-
This is my code error.
I have downloaded laion/CLIP-ViT-H-14-laion2B-s32B-b79K/
And it was placed under t2v_enhanced.
But it seems that the path does not quite match this rule with the data.
E…
-
I'm wondering if anyone has any configuration info they could share on training with CLAP embeddings?
I want to try the `laion/larger_clap_music` model from Huggingface, but it's really unclear to me…
-
I run the following command:
python prepare.py
The result is as follows:
error: RPC failed; curl 56 GnuTLS recv error (-110): The TLS connection was non-properly terminated.
fatal: The remote …
-
Congratulations for executing the herculean effort of putting together this dataset!
Where can one find the access information for the data in s3://s-laion-audio/?
-
I've been trying to train diffusion model with stable audio 1.0 config, I also trained the autoencoder with the Stable Audio 1.0 VAE for 50k steps [autoencoder result](https://storage.googleapis.com/…
-
https://github.com/LAION-AI/CLIP_benchmark/blob/main/clip_benchmark/metrics/zeroshot_classification.py#L44
-
Now that we have open-sourced COCA which is SOTA at image captioning, I think it's better to use it instead of BLIP.
https://huggingface.co/spaces/laion/CoCa