From fa5e0a38da4a1c51fafb290b22dbde7a978c54f4 Mon Sep 17 00:00:00 2001 From: Vladimir Mandic Date: Sun, 10 Sep 2023 20:42:14 -0400 Subject: [PATCH] update todo --- CHANGELOG.md | 3 ++- TODO.md | 10 ++++------ 2 files changed, 6 insertions(+), 7 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index c7758307c..b7106236e 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -10,7 +10,8 @@ Mostly a service release - find previews for already downloaded models or loras - **hires** enable non-latent upscale modes (standard upscalers) for both *original* and *diffusers* backend - note: when using refiner, latent upscale works before refiner pass, but non-latent upscale works after refiner pass + - when using non-latent upscalers, hires is now skipped - hires is only used for latent upscale + - when using refiner, latent upscale works before refiner pass, but non-latent upscale works after refiner pass - new option **inference mode** - default is standard `torch.no_grad` new option is `torch.inference_only` which is slightly faster and uses less vram, but only works on some gpus diff --git a/TODO.md b/TODO.md index 2ee1c56d3..8c5441e7a 100644 --- a/TODO.md +++ b/TODO.md @@ -22,7 +22,6 @@ Stuff to be added, in no particular order... - Port **A1111** stuff - Port `p.all_hr_prompts` - Import core repos to reduce dependencies - - Parse StabilityAI `modelspec` metadata - Non-technical: - Update Wiki - Get more high-quality upscalers @@ -34,11 +33,12 @@ Stuff to be added, in no particular order... - XYZ grid upscalers - Built-in `motd`-style notifications - Docker PR + - Add force hires - New Major - - Style editor (use json format instead of csv) - - Profile manager (for config.json and ui-config.json) + - Style editor + - Profile manager (for `config.json` and `ui-config.json`) - Multi-user support - - Add [SAG](https://huggingface.co/docs/diffusers/v0.19.3/en/api/pipelines/self_attention_guidance),(https://github.com/ashen-sensored/sd_webui_SAG) + - Add [SAG](https://huggingface.co/docs/diffusers/v0.19.3/en/api/pipelines/self_attention_guidance), [SAG](https://github.com/ashen-sensored/sd_webui_SAG) - Image phash and hdash using `imagehash` - Model merge using `git-rebasin` - Enable refiner-style workflow for `ldm` backend @@ -50,11 +50,9 @@ Stuff to be added, in no particular order... - Templates for SD-XL training - Lora train UI - Redesign - - Extensions reporting framework - New UI - New inpainting canvas controls (move from backend to purely frontend) - New image browser (move from backend to purely frontend) - - New extra networks (move from backend to purely frontend) - Change workflows from static/legacy to steps-based ## Investigate