diff --git a/CHANGELOG.md b/CHANGELOG.md index af5a8b9d4..417fef867 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,11 +1,11 @@ # Change Log for SD.Next -## Update for 2025-09-14 +## Update for 2025-09-15 -### Highlights for 2025-09-14 +### Highlights for 2025-09-15 -*What's new*? Big one is that we're (finally) switching the default UI to **ModernUI**! -StandardUI is still available and can be selected in settings, but ModernUI is now the default for new installs +*What's new*? Big one is that we're (*finally*) switching the default UI to **ModernUI**! +**StandardUI** is still available and can be selected in settings, but ModernUI is now the default for new installs *What's else*? **Chroma** is in its final form, there are several new **Qwen-Image** variants and **Nunchaku** hit version 1.0! Also, there are quite a few offloading improvements and many quality-of-life changes to UI and overal workflows @@ -13,7 +13,7 @@ And check out new **history** tab in the right panel, it now shows visualization [ReadMe](https://github.com/vladmandic/automatic/blob/master/README.md) | [ChangeLog](https://github.com/vladmandic/automatic/blob/master/CHANGELOG.md) | [Docs](https://vladmandic.github.io/sdnext-docs/) | [WiKi](https://github.com/vladmandic/automatic/wiki) | [Discord](https://discord.com/invite/sd-next-federal-batch-inspectors-1101998836328697867) | [Sponsor](https://github.com/sponsors/vladmandic) -### Details for 2025-09-14 +### Details for 2025-09-15 - **Models** - **Chroma** final versions: [Chroma1-HD](https://huggingface.co/lodestones/Chroma1-HD), [Chroma1-Base](https://huggingface.co/lodestones/Chroma1-Base) and [Chroma1-Flash](https://huggingface.co/lodestones/Chroma1-Flash) diff --git a/TODO.md b/TODO.md index d2e4e6306..dce3ad49e 100644 --- a/TODO.md +++ b/TODO.md @@ -15,8 +15,6 @@ Main ToDo list can be found at [GitHub projects](https://github.com/users/vladma ### Blocked items -- Upgrade: `pydantic` - - see - Upgrade: `albumentations` - blocked by `insightface` @@ -34,9 +32,9 @@ Main ToDo list can be found at [GitHub projects](https://github.com/users/vladma - [SUPIR upscaler](https://github.com/Fanghua-Yu/SUPIR) - [ByteDance OneReward](https://github.com/bytedance/OneReward) - [ByteDance USO](https://github.com/bytedance/USO) -- Remove: Agent Scheduler -- Remove: CodeFormer -- Remove: GFPGAN +- Remove: `Agent Scheduler` +- Remove: `CodeFormer` +- Remove: `GFPGAN` - ModernUI: Lite vs Expert mode - Engine: TensorRT acceleration diff --git a/modules/sd_offload.py b/modules/sd_offload.py index d2e556522..f195591f1 100644 --- a/modules/sd_offload.py +++ b/modules/sd_offload.py @@ -78,6 +78,8 @@ def apply_group_offload(sd_model, op:str='model'): 'record_stream': shared.opts.group_offload_record, 'low_cpu_mem_usage': False, } + if shared.opts.group_offload_type == 'block_level': + offload_dct['exclude_modules'] = ['vae'] shared.log.debug(f'Setting {op}: offload={shared.opts.diffusers_offload_mode} options={offload_dct}') if hasattr(sd_model, "enable_group_offload"): sd_model.enable_group_offload(**offload_dct)