mirror of
https://github.com/vladmandic/automatic
synced 2026-09-20 01:31:13 +02:00
update changelog and todo
Signed-off-by: Vladimir Mandic <mandic00@live.com>
This commit is contained in:
+4
-3
@@ -1,6 +1,6 @@
|
||||
# Change Log for SD.Next
|
||||
|
||||
## Highlights for 2026-08-22
|
||||
## Highlights for 2026-08-23
|
||||
|
||||
Time for a new release, this is a larger one!
|
||||
Main focus is improving video workflows which also brings full support for new [MiniMax H3](https://vladmandic.github.io/sdnext-docs/MiniMax) and [LTXVideo-2.5](https://vladmandic.github.io/sdnext-docs/LTX)
|
||||
@@ -17,7 +17,7 @@ Plus quite a lot more, see full [changelog](https://github.com/vladmandic/automa
|
||||
|
||||
[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 2026-08-22
|
||||
## Details for 2026-08-23
|
||||
|
||||
- **Models**
|
||||
- [MiniMax H3](https://huggingface.co/MiniMaxAI/MiniMax-H3) available in *base* and *ref* variants
|
||||
@@ -83,7 +83,7 @@ Plus quite a lot more, see full [changelog](https://github.com/vladmandic/automa
|
||||
may provide significant speed-up on some gpus, disabled by default
|
||||
- AR display ratio on manual resolution change
|
||||
- **Wiki**
|
||||
- major updates: *Offload, Detailer, Video, MiniMax, LTX*
|
||||
- major updates: *Offload, Detailer, Video, MiniMax, LTX, Debug*
|
||||
- minor updates: *Intel-ARC, FramePack, Parameters, API, Installation, SDNQ-Quantization, CLI-Arguments*
|
||||
- **Removed**
|
||||
- remove DirectML support
|
||||
@@ -114,6 +114,7 @@ Plus quite a lot more, see full [changelog](https://github.com/vladmandic/automa
|
||||
- scripts: mixture-of-diffusers and mixture-tiling update to use igwn-segments
|
||||
- api: process
|
||||
- api: auth via remote-ip
|
||||
- api: improve response models
|
||||
- krea2: fallback to base pipeline/transformer for nunchaku-lite
|
||||
- torchsde: handle obsolete dependency
|
||||
- upscaler: avoid unnecessary multi-pass
|
||||
|
||||
@@ -3,9 +3,9 @@
|
||||
## Short-term
|
||||
|
||||
- Update LTX wiki, @CalamitousFelicitousness
|
||||
- Lora: new handler, @CalamitousFelicitousness
|
||||
- Productize benchmark tool, @CalamitousFelicitousness
|
||||
- Inpaint: https://discord.com/channels/1101998836328697867/1130536562422186044/1506850651035144322, @vladmandic
|
||||
- Lora: new handler, @CalamitousFelicitousness
|
||||
- Control tab verify overrides handling, @vladmandic
|
||||
- Create pre-quant for LTX-2.5
|
||||
- Create pre-quant for MiniMax-H3-Turbo
|
||||
|
||||
+1
-1
Submodule wiki updated: f2c955021c...b974e50847
Reference in New Issue
Block a user