update changelog

This commit is contained in:
Vladimir Mandic
2024-09-07 12:14:18 -04:00
parent 8f0d08e9a4
commit 7cd72b5d9a
+9 -11
View File
@@ -4,28 +4,26 @@
### Highlights for 2024-09-07
Major refactor of [FLUX.1](https://blackforestlabs.ai/announcing-black-forest-labs/) support:
- Full **ControlNet** support, better **LoRA** support, full **prompt attention** support,
- Faster execution, more flexible loading, additional quantization options, and more...
Major refactor of [FLUX.1](https://blackforestlabs.ai/announcing-black-forest-labs/) support:
- Full **ControlNet** support, better **LoRA** support, full **prompt attention** support,
- Faster execution, more flexible loading, additional quantization options, and more...
- Added **image-to-image**, **inpaint**, **outpaint**, **hires** modes
- Since both *Optimum-Quanto* and *BitsAndBytes* libraries are limited in their platform support matrix,
try enabling **NNCF** for quantization/compression on-the-fly!
try enabling **NNCF** for quantization/compression on-the-fly!
Few image related goodies...
- **Context-aware** image resize that allows for img2img or inpaint even at massively different aspect ratios!
Few image related goodies...
- **Context-aware** image resize that allows for *img2img* or *inpaint* even at massively different aspect ratios!
- Auto **HDR** image create for SD and SDXL with both 16ch true-HDR and 8-ch HDR-effect images ;)
And few video related goodies...
And few video related goodies...
- [CogVideoX](https://huggingface.co/THUDM/CogVideoX-5b) 2b and 5b variants
with support for *text-to-video* and *video-to-video*!
- **AnimateDiff** prompt travel and long context windows!
- [AnimateDiff](https://github.com/guoyww/animatediff/) prompt travel and long context windows!
create video which travels between different prompts and at long video lengths!
Oh, as a sidenote, and also new
Plus tons of minor items and fixes - see [changelog](https://github.com/vladmandic/automatic/blob/master/CHANGELOG.md) for details!
### Details for 2024-09-05
### Details for 2024-09-07
**Major refactor of FLUX.1 support:**
- allow configuration of individual FLUX.1 model components: *transformer, text-encoder, vae*