From 37dfedb8ff6e9498c0cb4c920f1972350a63e689 Mon Sep 17 00:00:00 2001 From: Vladimir Mandic Date: Fri, 31 Jul 2026 15:20:42 +0200 Subject: [PATCH] update changelog Signed-off-by: Vladimir Mandic --- CHANGELOG.md | 10 +++++----- data/reference-base.json | 8 -------- 2 files changed, 5 insertions(+), 13 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index ead928686..bb116e498 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,19 +3,19 @@ ## Update for 2026-07-31 - **Models** - - [SeFi-Image](https://huggingface.co/SeFi-Image/SeFi-Image-5B-RL) in *Base*, *Turbo* (distilled) and *RL* (finetuned) variants + - [SeFi-Image](https://huggingface.co/SeFi-Image/SeFi-Image-5B-RL) in *Base* and *Turbo* (distilled) variants SeFi is an interesting model that separates generation into semantic and texture latent streams and denoising semantic structure slightly ahead of texture details - SeFi comes in 1B, 2B and 5B variants + SeFi comes in sizes with 1B, 2B and 5B params - [Microsoft Mage-Flow](https://huggingface.co/mage-flow-community/Mage-Flow) in *Base* and *Turbo* (distilled) variants Mage-Flow is a 4B-scale generative stack for efficient text-to-image generation and instruction-based image editing *note*: Microsoft released and then unpublished the model, but we still have a mirror available for download - **Features** - - startup: optimized server startup - - process: preserve audio when processing video - video: support for scripts/extensions - prompt enhance: support for video generation - - remove background: add [lucida](https://huggingface.co/egeorcun/lucida) model + - startup: optimized server startup + - process: preserve audio when processing video + - remove background: new [lucida](https://huggingface.co/egeorcun/lucida) model - **Fixes** - seedvr quality - skip-all do not skip env init diff --git a/data/reference-base.json b/data/reference-base.json index dba2f0ce1..760540bf3 100644 --- a/data/reference-base.json +++ b/data/reference-base.json @@ -950,13 +950,5 @@ "extras": "sampler: Default", "size": 0, "date": "2026 July" - }, - "SeFi-Image 5B RL": { - "path": "vladmandic/SeFi-Image-5B-RL", - "preview": "vladmandic--SeFi-Image-5B-RL.jpg", - "desc": "SeFi-Image is a text-to-image foundation model family built with Semantic-First Diffusion. It separates generation into semantic and texture latent streams, denoising semantic structure slightly ahead of texture details.", - "extras": "sampler: Default", - "size": 0, - "date": "2026 July" } }