GitLab

You can use the CLIPLoader to use the t5xxl only or the DualCLIPLoader to
use CLIP-L and CLIP-G only for sd3.

I was going to completely remove this function because it is unmaintainable
but I think this is the best compromise.

The clip skip and v_prediction parts of the configs should still work but
not the fp16 vs fp32.

Logging level now defaults to info. --verbose sets it to debug.

Fix issue with not loading the SSD1B clip correctly.

The effnet can be used to encode images for img2img with Stage C.

This node is unfinished, SVD checkpoints saved with this node will
work with ComfyUI but not with anything else.

This is an old model.

Load the checkpoint like a regular one and use the new
SD_4XUpscale_Conditioning node.

Replace constants with downscale_ratio and latent_channels.

They will show up if both the taesd_encoder and taesd_decoder or taesdxl
model files are present in the models/vae_approx directory.

Pytorch supports two variants of fp8:
--fp8_e4m3fn-text-enc (the one that seems to give better results)
--fp8_e5m2-text-enc