Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-19 01:04:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

framepack add f1 model

Browse Source 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
This commit is contained in:
Vladimir Mandic
2025-05-04 18:58:53 -04:00
parent 5971f67e4f
commit f534ee8c52
1 changed files with 8 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+8 -6
View File
@@ -2,16 +2,18 @@
## Update for 2025-05-04
- **Features**
- Prompt-Enhhance: add **Qwen3** 0.6B/1.7B/4B models
- Prompt-Enhhance: add thinking mode support (for models that have it)
- **Features**
- [FramePack](https://github.com/vladmandic/sd-extension-framepack)
support for **T2V** in addition to **I2V** and **FLF2V**
support for new **F1: forward-only** model variant in addition to regular **bi-directional**
- **Prompt-Enhhance**
add **Qwen3** *0.6B/1.7B/4B* models
add thinking mode support (for models that have it)
- [HiDream-E1](https://huggingface.co/HiDream-ai/HiDream-E1-Full) natural language image-editing model built on HiDream-I1
available via *networks -> models -> reference*
*note*: right now hidream-e1 is limited to 768x768 images, so you must force resize image before running it
- [FramePack](https://github.com/vladmandic/sd-extension-framepack)
support for **T2V** in addition to **I2V** and **FLF2V**
- **Other**
- CUDA: set default to `torch==2.7.0` with `cuda==12.8`
- CUDA: set default to `torch==2.7.0` with `cuda==12.8`
- FramePack: improve performance
- Docker: pre-install `ffmpeg`
- Wiki: updated pages: *Video, ROCm, ZLUDA, Quantization*