nac2100

poor image quality compared to AUTOMATIC1111

3

  This reason seems to be lack of skip_clip and no negative prompt support, for txt2img will this be support in future?

Is the generation_config important during LoRa fine-tuning? If we aim for inference at a high temperature setting (e.g., 0.9), is it advisable to train at the same setting, or should...

[REQUEST] DeepSpeed-FastGen AWQ support

3

**Is your feature request related to a problem? Please describe.** Without 4bit quantization the batch size is limited **Describe the solution you'd like** Add AWQ support, just like TGI **Describe...

Balancing Parallel Jobs Across Workers in BullMQ Pro

1

I am interested in the Pro version of BullMQ, but I don't see any documentation on how to balance parallel jobs across workers. For example, if there are 3 workers,...