From 8390ac02a2bd4daf596bb97964309d93e5020d0e Mon Sep 17 00:00:00 2001 From: Vladimir Mandic Date: Fri, 11 Apr 2025 23:39:41 -0400 Subject: [PATCH] update changelog Signed-off-by: Vladimir Mandic --- CHANGELOG.md | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 3ddcea45d..2a7b34fa4 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,6 +1,6 @@ # Change Log for SD.Next -## Update for 2025-04-11 +## Update for 2025-04-12 - **Models** - [HiDream-I1](https://huggingface.co/HiDream-ai/HiDream-I1-Full) in fast, dev and full variants! @@ -8,10 +8,9 @@ and 4 (!?) text-encoders: *clip-l, clip-g, t5-1.1-xxl, llama-3.1-8b-instruct* for total of **8.3B** parameters simply select from *networks -> models -> reference* due to size (over 25B params in 58GB), offloading and on-the-fly quantization are pretty much a necessity - custom `llama` model can be set in *settings -> model options* + custom `llama` model can be set in *settings -> model options* difference between variants is recommended number of steps: *fast=16, dev=28, full=50* - hidream supportability: *offloading, quantization, taesd live-preview, remote-vae* - hidream compatibility: *flowmatching samplers* + compatible with: *flowmatching samplers*, *offloading, quantization, taesd live-preview* - **Features** - Custom model loader can be used to load any known diffusion model with default or custom model components