From 6f7a446644a75b20da457986bcc4f3e59ab9ee59 Mon Sep 17 00:00:00 2001 From: Vladimir Mandic Date: Wed, 18 Sep 2024 16:22:59 -0400 Subject: [PATCH] add reference note --- CHANGELOG.md | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 74d8185b1..d2db25749 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -35,8 +35,9 @@ will automatically find appropriate encoder in the loaded model and replace it with loaded text encoder download text encoders into folder set in settings -> system paths -> text encoders default `models/Text-encoder` folder is used if no custom path is set - example *clip-vit-l* models: [Detailed, Smooth](https://huggingface.co/zer0int/CLIP-GmP-ViT-L-14), [LongCLIP](https://huggingface.co/zer0int/LongCLIP-GmP-ViT-L-14) - example *clip-vit-g* models: [OpenCLIP-Laion2b](https://huggingface.co/collections/laion/openclip-laion-2b-64fcade42d20ced4e9389b30) + finetuned *clip-vit-l* models: [Detailed, Smooth](https://huggingface.co/zer0int/CLIP-GmP-ViT-L-14), [LongCLIP](https://huggingface.co/zer0int/LongCLIP-GmP-ViT-L-14) + reference *clip-vit-l* and *clip-vit-g* models: [OpenCLIP-Laion2b](https://huggingface.co/collections/laion/openclip-laion-2b-64fcade42d20ced4e9389b30) + *note* sd/sdxl contain heavily distilled versions of reference models, so switching to reference model produces vastly different results - xyz grid support for text encoder - full prompt parser now correctly works with different prompts in batch - **huggingface**: