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

support sdxl packaged without vae

Browse Source 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
This commit is contained in:
Vladimir Mandic
2025-05-11 14:49:26 -04:00
parent 4eedeab9f8
commit a6e6c6ce5e
2 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+4 -1
View File
@@ -1,12 +1,14 @@
# Change Log for SD.Next
## Update for 2025-05-10
## Update for 2025-05-11
- **Compute**
- **NNCF**
- Faster quantization
- Faster inference with support for `torch.triton`
up to 3.5x faster with INT4 and 2x faster with INT8
- New settings: *NNCF -> Number of quantization groups*
default is a balance between performance (lower settings) and quality (larger setting)
- **ZLUDA**:
- *warning*: AMD Adrenaline 25.5.1 drivers are NOT COMPATIBLE with ZLUDA
see [issue](https://github.com/vladmandic/sdnext/issues/3918) for details
@@ -33,6 +35,7 @@
supports text, image and video prompts with or without input image
*note*: if input image is provided, model should be left at default `gemma-3-4b-it` as most other LLMs do not support hybrid workflows
- **Fixes**
- Model load: support SDXL safetensors packaged without VAE
- ROCm: disable cuDNN benchmark, fixes slow MIOpen tuning with `torch==2.7`
- Extensions: use in-process installer for extensions-builtin, improves startup performance
- FramePack: monkey-patch for dynamically installed `av`
modules/sd_detect.py
+1 -1
View File
@@ -40,7 +40,7 @@ def detect_pipeline(f: str, op: str = 'model', warning=True, quiet=False):
guess = 'Stable Diffusion XL Refiner'
elif (size > 5692 and size < 5698) or (size > 4134 and size < 4138) or (size > 10362 and size < 10366) or (size > 15028 and size < 15228):
guess = 'Stable Diffusion 3'
elif (size >= 6611 and size <= 7220): # 6617, HassakuXL is 6776, monkrenRealisticINT_v10 is 7217
elif (size >= 6420 and size <= 7220): # 6420, IustriousRedux is 6541, monkrenRealisticINT_v10 is 7217
guess = 'Stable Diffusion XL'
elif (size >= 9791 and size <= 9799): # 9794
guess = 'Stable Diffusion XL Instruct'