Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-19 09:14:35 +02:00
Code Issues Packages Projects Releases Wiki Activity

update changelog/todo/wiki

Browse Source 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
This commit is contained in:
Vladimir Mandic
2026-07-05 20:22:05 +02:00
parent 9da4eb04dd
commit e85272aa8a
3 changed files with 14 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+7 -3
View File
@@ -1,8 +1,8 @@
# Change Log for SD.Next
## Update for 2026-07-04
## Update for 2026-07-05
### Highlights for 2026-07-04
### Highlights for 2026-07-05
Service-pack update with number of fixes and quality-of-life improvements
Plus few new models: **Krea 2**, **Boogu**, **Photoroom PRXPixel**, **FLUX.2 Klein KV** and some new community models
@@ -11,7 +11,7 @@ Also couple of *experimental* features: see below for details...
[Home](https://vladmandic.github.io/sdnext/) | [ChangeLog](https://github.com/vladmandic/automatic/blob/master/CHANGELOG.md) | [Docs](https://vladmandic.github.io/sdnext-docs/) | [Discord](https://discord.com/invite/sd-next-federal-batch-inspectors-1101998836328697867) | [Sponsor](https://github.com/sponsors/vladmandic)
### Details for 2026-07-04
### Details for 2026-07-05
- **Models**
- [Krea 2](https://www.krea.ai/blog/krea-2-image-model) in *base* and *turbo* (distilled) variants
@@ -51,6 +51,9 @@ Also couple of *experimental* features: see below for details...
- preview now only runs if output panel is visible
- ModernUI: old *txt2img* and *img2img* tabs are marked as legacy and hidden by default
- StandardUI: marked as legacy
- **Wiki**
- new [Performance Timers](wiki/Performance-Timers) page with detailed explanation of all timers and what to tune for performance
- new [Model Loading](wiki/Model-Loading) page with detailed explanation of model loading
- **Internal**
- delay init of video models
- **Experimental**
@@ -92,6 +95,7 @@ Also couple of *experimental* features: see below for details...
- text-encode: restore hijack on pipeline switch
- vae: restore hijack on pipeline switch
- startup: faster model storage checks
- installer: double-restart on diffusers/transformers upgrade
## Update for 2026-06-16
TODO.md
+6 -5
View File
@@ -8,12 +8,12 @@
### Assigned
- [Object clear](https://huggingface.co/jixin0101/ObjectClear) remover for Kanvas, @vladmandic
- Chat-based interface, @vladmandic
- Control tab verify overrides handling, @vladmandic
- [nVidia LocateAnything](https://huggingface.co/nvidia/LocateAnything-3B) detection for Detailer, @vladmandic
- [Object clear](https://huggingface.co/jixin0101/ObjectClear) remover for Kanvas, @vladmandic
- Cloud providers, @CalamitousFelicitousness
- Video processing add full API support, @CalamitousFelicitousness
- Video processing add/verify full API support, @CalamitousFelicitousness
- Storage analyzer, @vladmandic
### Unassigned
@@ -31,11 +31,12 @@
- Integrate natural language image search
- [ImageDB](https://github.com/vladmandic/imagedb)
- Unify *huggingface* and *diffusers* model folders
- [QuantFunc](https://huggingface.co/QuantFunc/Klein-9B-Series)
### OnHold
- Implement [nvvfx](https://pypi.org/project/nvidia-vfx/): not compatible with latest nVidia drivers
- [nVidia-VFX](https://pypi.org/project/nvidia-vfx/): not compatible with latest nVidia drivers
- [QuantFunc](https://huggingface.co/QuantFunc/Klein-9B-Series): once its released as sdk
- [nVidia LocateAnything](https://huggingface.co/nvidia/LocateAnything-3B) detection for Detailer, once its compatible with transformers==5
- LoRA add OMI format support for SD35/FLUX.1
- Remote Text-Encoder support, sidelined for the moment
- Multi-user support
wiki
+1 -1
Submodule wiki updated: 9512e471af...84ac82182e