From 32906a20eebb8eaf6b4edab90f2889e625c1db30 Mon Sep 17 00:00:00 2001 From: Vladimir Mandic Date: Fri, 15 Aug 2025 07:54:52 -0400 Subject: [PATCH] update docker build Signed-off-by: Vladimir Mandic --- CHANGELOG.md | 26 ++++++++++++++++++-------- TODO.md | 7 ------- configs/Dockerfile.cuda | 4 ++-- modules/memstats.py | 2 +- package.json | 4 ++-- requirements.txt | 2 +- wiki | 2 +- 7 files changed, 25 insertions(+), 22 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 11d2882bc..d648b4e6b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,21 +1,28 @@ # Change Log for SD.Next -## Update for 2025-08-14 +## Update for 2025-08-15 -### Highlights for 2025-08-14 +### Highlights for 2025-08-15 -Several new models: [Qwen-Image](https://qwenlm.github.io/blog/qwen-image/) (plus *Lightning* variant) and [FLUX.1-Krea-Dev](https://www.krea.ai/blog/flux-krea-open-source-release) -Several updated models: [Chroma](https://huggingface.co/lodestones/Chroma), [SkyReels-V2](https://huggingface.co/Skywork/SkyReels-V2-DF-14B-720P-Diffusers), [Wan-VACE](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B-diffusers), [HunyuanDiT](https://huggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.2-Diffusers-Distilled) -Plus continuing with major **UI** work, we have new embedded **Docs/Wiki** search, redesigned real-time **hints**, **wildcards** UI selector, built-in **GPU monitor**, **CivitAI** integration and more! -On the compute side, new profiles for high-vram GPUs, offloading improvements, parallel-load for large models, support for new `torch` release and improved quality when using low-bit quantization! -And (*as always*) many bugfixes and improvements to existing features! +New release two weeks after the last one and its a big one with over 150 commits! +- Several new models: [Qwen-Image](https://qwenlm.github.io/blog/qwen-image/) (plus *Lightning* variant) and [FLUX.1-Krea-Dev](https://www.krea.ai/blog/flux-krea-open-source-release) +- Several updated models: [Chroma](https://huggingface.co/lodestones/Chroma), [SkyReels-V2](https://huggingface.co/Skywork/SkyReels-V2-DF-14B-720P-Diffusers), [Wan-VACE](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B-diffusers), [HunyuanDiT](https://huggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.2-Diffusers-Distilled) +- Plus continuing with major **UI** work with new embedded **Docs/Wiki** search, redesigned real-time **hints**, **wildcards** UI selector, built-in **GPU monitor**, **CivitAI** integration and more! +- On the compute side, new profiles for high-vram GPUs, offloading improvements, parallel-load for large models, support for new `torch` release and improved quality when using low-bit quantization! +- And (*as always*) many bugfixes and improvements to existing features! + +We're also announcing **SD.Next Model Samples Gallery**, a pre-generated image gallery with 60 models (45 base and 15 finetunes) and 40 different styles resulting in 2,400 high resolution images! +Gallery additionally includes model details such as typical load and inference times as well as sizes and types of each model component (*e.g. unet, transformer, text-encoder, vae*) +[Live page](https://vladmandic.github.io/sd-samples/compare.html) | [GitHub repo](https://github.com/vladmandic/sd-samples) + +![sd-samples](https://github.com/user-attachments/assets/3efc8603-0766-4e4e-a4cb-d8c9b13d1e1d) *Note*: Change-in-behavior - locations of downloaded HuggingFace models and components are changed to allow for de-duplication of common modules and switched from using system default cache folder to `models/huggingface` SD.Next will warn on startup on unused cache entries that can be removed. Also, to take advantage of de-duplication, you'll need to delete models from your `models/Diffusers` folder and let SD.Next re-download them! [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) -### Details for 2025-08-14 +### Details for 2025-08-15 - **Models** - [Qwen-Image](https://qwenlm.github.io/blog/qwen-image/) @@ -132,6 +139,9 @@ SD.Next will warn on startup on unused cache entries that can be removed. Also, - new unified pipeline component loader in `pipelines/generic` - remove **LDSR** - remove `api-only` cli option +- **Docker** + - update cuda base image: `pytorch/pytorch:2.8.0-cuda12.8-cudnn9-runtime` + - update official builds: - **Fixes** - refactor legacy processing loop - fix settings components mismatch diff --git a/TODO.md b/TODO.md index f3371e091..389be8963 100644 --- a/TODO.md +++ b/TODO.md @@ -2,10 +2,6 @@ Main ToDo list can be found at [GitHub projects](https://github.com/users/vladmandic/projects) -## Current Candidates - -- `HF_ENABLE_PARALLEL_LOADING` - ## Future Candidates - Remote TE @@ -78,7 +74,6 @@ Main ToDo list can be found at [GitHub projects](https://github.com/users/vladma - control: support scripts via api - fc: autodetect distilled based on model - fc: autodetect tensor format based on model -- flux: loader for civitai nf4 models - hypertile: vae breaks when using non-standard sizes - install: enable ROCm for windows when available - loader: load receipe @@ -86,8 +81,6 @@ Main ToDo list can be found at [GitHub projects](https://github.com/users/vladma - lora: add other quantization types - lora: add t5 key support for sd35/f1 - lora: maybe force imediate quantization -- model load: add ChromaControlPipeline, ChromaInpaintPipeline -- model load: cogview4 balanced offload does not work for GlmModel - model load: force-reloading entire model as loading transformers only leads to massive memory usage - model load: group offload - model load: implement model in-memory caching diff --git a/configs/Dockerfile.cuda b/configs/Dockerfile.cuda index ca117bd4c..4e5a496e1 100644 --- a/configs/Dockerfile.cuda +++ b/configs/Dockerfile.cuda @@ -2,7 +2,7 @@ # docs: # base image -FROM pytorch/pytorch:2.7.0-cuda12.8-cudnn9-runtime +FROM pytorch/pytorch:2.8.0-cuda12.8-cudnn9-runtime # metadata LABEL org.opencontainers.image.vendor="SD.Next" @@ -13,7 +13,7 @@ LABEL org.opencontainers.image.source="https://github.com/vladmandic/sdnext/" LABEL org.opencontainers.image.licenses="AGPL-3.0" LABEL org.opencontainers.image.title="SD.Next" LABEL org.opencontainers.image.description="SD.Next: Advanced Implementation of Stable Diffusion and other Diffusion-based generative image models" -LABEL org.opencontainers.image.base.name="https://hub.docker.com/pytorch/pytorch:2.7.0-cuda12.8-cudnn9-runtime" +LABEL org.opencontainers.image.base.name="https://hub.docker.com/pytorch/pytorch:2.8.0-cuda12.8-cudnn9-runtime" LABEL org.opencontainers.image.version="latest" # minimum install diff --git a/modules/memstats.py b/modules/memstats.py index 1e2be27c8..fdc94df37 100644 --- a/modules/memstats.py +++ b/modules/memstats.py @@ -86,7 +86,7 @@ def gpu_stats(): gpu['error'] = str(e) if not fail_once: shared.log.error(f'GPU stats: {e}') - errors.display(e, 'GPU stats') + # errors.display(e, 'GPU stats') fail_once = True return gpu diff --git a/package.json b/package.json index 07b2681ec..1b0b95bca 100644 --- a/package.json +++ b/package.json @@ -1,7 +1,7 @@ { "name": "@vladmandic/sdnext", "version": "dev", - "description": "SD.Next: Opinionated implementation of Stable Diffusion", + "description": "SD.Next: All-in-one WebUI for AI generative image and video creation", "author": "Vladimir Mandic ", "bugs": { "url": "https://github.com/vladmandic/sdnext/issues" @@ -19,7 +19,7 @@ "venv": ". venv/bin/activate", "start": ". venv/bin/activate; python launch.py --debug", "localize": "node cli/localize.js", - "packages": ". venv/bin/activate && pip install --upgrade transformers accelerate huggingface_hub safetensors tokenizers peft compel pytorch_lightning", + "packages": ". venv/bin/activate && pip install --upgrade transformers accelerate huggingface_hub safetensors tokenizers peft compel pytorch_lightning pylint ruff", "eslint": "eslint . javascript/ extensions-builtin/sdnext-modernui/javascript/", "ruff": ". venv/bin/activate && ruff check", "pylint": ". venv/bin/activate && pylint *.py modules/ pipelines/ scripts/ extensions-builtin/ | grep -v '^*'", diff --git a/requirements.txt b/requirements.txt index f304e5c15..20fe134c3 100644 --- a/requirements.txt +++ b/requirements.txt @@ -47,7 +47,7 @@ einops==0.8.1 huggingface_hub==0.34.4 numexpr==2.11.0 numpy==2.1.2 -pandas==2.3.0 +pandas==2.3.1 numba==0.61.2 protobuf==4.25.3 pytorch_lightning==2.5.3 diff --git a/wiki b/wiki index fe2558394..f91e819d2 160000 --- a/wiki +++ b/wiki @@ -1 +1 @@ -Subproject commit fe255839498563e30bf1a1db9b5f43a36e1196c6 +Subproject commit f91e819d22603f34be0c3e8fb674d4ab89421622