-
Hello,
I’m considering using the LilyGo T-Deck as a portable device for a project that involves frequency scanning and data transmission. My goal is to connect a CC1101 transceiver to the T-Deck for …
-
Dynamic LoRA (Low-Rank Adaptation) switching functionality, allowing users to change LoRA models on-the-fly during inference without reloading the entire model.
-
Hello, thanks for sharing the great work!
I download the checkpoint of repllama from huggiface. I encode the query and passages with this checkpoint and find the result I got is MRR@10: 39.69, while …
-
https://huggingface.co/ByteDance/Hyper-SD
Can we make the origial FLUX model Hyper version, than train on it?
-
### Bug description
I ran into the following issue while running LoRA fine-tuning.
**Stack Trace**
```
KeyError: Caught KeyError in DataLoader worker process 0.
Original Traceback (most recent …
-
Is there a way to sort tags by class, or category?
So for example, it would be sort my category, like [Character's physical features > outfits > furniture/background objects > locations > actions > e…
-
Following the `README.md`, I tested the `subject_driven_generation`:
```bash
sh train_sdxl_lora_cat.sh
python3 infer.py
```
and got low-quality images from mixer model, while the vanilla lora rem…
-
Right now scheduling SD LoRAs is a real riddle. Registering hooks, managing keyframes and 3 different applying nodes, none of which has model output. And no clues on a correct order to connect all thi…
-
Is it possible to set the lora [sdxl_train_network.py] text encoder learning rate separately?
similar to Flux,
In Clip_L there are 4.45 times fewer parameters than Clip_G.
As a result, the Text-En…
-
`!!! Exception during processing !!! cannot access local variable 'image1' where it is not associated with a value
Traceback (most recent call last):
File "C:\Users\Robert\Downloads\ComfyUI_window…