A smaller version of text_encoder, please.

by razvanab - opened Jun 19

Jun 19

Is there a smaller version of the text encoder? 10G is quite large, and I would prefer to make better use of that space with other checkpoints and Loras.
Thank you.

Jason233

Jul 19

did some body tried replace it by t5_v1_1_large or xl ?

sayakpaul

PixArt org Jul 19

Check out https://huggingface.co/docs/diffusers/en/api/pipelines/pixart#inference-with-under-8gb-gpu-vram.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment