GitLab

but faster.

load_model_gpu() is now used with the text encoder models instead of just
the unet.

This is faster on big text encoder models than running it on the CPU.

If the same node id with the same class exists between two executions the
same instance will be used.

This means you can now cache things in nodes for more efficiency.

* Add link to 7z in README

* Change 7z to 7-Zip

The stability streamlit example passes a zero cond as the negative input
so using this for the negative input makes outputs match the streamlit.

Add a new argument --use-quad-cross-attention

The created checkpoints contain workflow metadata that can be loaded by
dragging them on top of the UI or loading them with the "Load" button.

Checkpoints will be saved in fp16 or fp32 depending on the format ComfyUI
is using for inference on your hardware. To force fp32 use: --force-fp32

Anything that patches the model weights like merging or loras will be
saved.

The output directory is currently set to: output/checkpoints but that might
change in the future.

Update LoadClip to load clip models for SDXL refiner.