DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-12 03:49:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: add TAEQI2.1 support for Qwen Image 2.1 (#2123)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-10-11 00:01:18 +08:00
1 parent 1b0ba10893
commit 2988060a43
4 files changed
+53 -14
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/taesd.md
+12
View File
@@ -37,3 +37,15 @@ sd.cpp also supports [TAEHV](https://github.com/madebyollin/taehv) (#937), which
```
Then simply replace the `--vae xxx.safetensors` with `--tae xxx.safetensors` in the commands. If it still out of VRAM, add `--vae-conv-direct` to your command though might be slower.
### Qwen Image 2.1 (TAEQI2.1)
For Qwen Image 2.1, use [taeqi2_1](https://github.com/madebyollin/taesd), which supports 64-channel latents, 16x spatial scaling, and RGBA images.
Download the official [safetensors weights](https://huggingface.co/madebyollin/taeqi2_1/blob/main/taeqi2_1.safetensors) directly; no conversion is needed:
```bash
curl -L -o taeqi2_1.safetensors https://huggingface.co/madebyollin/taeqi2_1/resolve/main/taeqi2_1.safetensors
```
Replace `--vae PATH` with `--taesd taeqi2_1.safetensors` in the [Qwen Image 2.1 examples](qwen_image_2.1.md) to use it for encoding and decoding. For previews only, keep `--vae PATH` and add `--taesd taeqi2_1.safetensors --taesd-preview-only --preview tae`.