update changelog

Signed-off-by: vladmandic <mandic00@live.com>
pull/4509/head^2
vladmandic 2026-01-01 10:45:48 +01:00
parent 7a8d315e84
commit a37c70d668
3 changed files with 5 additions and 2 deletions

View File

@ -2,6 +2,9 @@
## Update for 2025-01-01
- **Models**
- [Qwen-Image-2512](https://huggingface.co/Qwen/Qwen-Image-2512)
Qwen-Image successor, significantly reduces the AI-generated look and adds finer natural detailils and improved text rendering
- **Feaures**
- **SDNQ** now has *19 int* based and *69 float* based quantization types
*note*: not all are exposed via ui purely for simplicity, but all are available via api and scripts

View File

@ -30,7 +30,7 @@ def load_qwen(checkpoint_info, diffusers_load_config=None):
diffusers.pipelines.auto_pipeline.AUTO_TEXT2IMAGE_PIPELINES_MAPPING["qwen-layered"] = diffusers.QwenImageLayeredPipeline
diffusers.pipelines.auto_pipeline.AUTO_IMAGE2IMAGE_PIPELINES_MAPPING["qwen-layered"] = diffusers.QwenImageLayeredPipeline
diffusers.pipelines.auto_pipeline.AUTO_INPAINT_PIPELINES_MAPPING["qwen-layered"] = diffusers.QwenImageLayeredPipeline
else:
else: # qwen-image, qwen-image-2512
cls_name = diffusers.QwenImagePipeline
diffusers.pipelines.auto_pipeline.AUTO_TEXT2IMAGE_PIPELINES_MAPPING["qwen-image"] = diffusers.QwenImagePipeline
diffusers.pipelines.auto_pipeline.AUTO_IMAGE2IMAGE_PIPELINES_MAPPING["qwen-image"] = diffusers.QwenImageImg2ImgPipeline

2
wiki

@ -1 +1 @@
Subproject commit b823ea47f93d1a22e5f5f8c72b65974748617721
Subproject commit 93c375c3a0c1ee8b3653dc62b975ce9b757ada0f