Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-19 17:24:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

add GLM-Image pipeline support

Browse Source 
- Add GLM-Image (zai-org/GLM-Image) model detection and loading
- Custom pipeline loader with proper component handling:
  - ByT5 text encoder (cannot use shared T5 due to different hidden size)
  - Vision-language encoder (9B AR model)
  - DiT transformer (7B)
- Fix EOS token early stopping in AR generation
- Add AR token generation progress tracking with terminal progress bar
- Fix uninitialized audio variable in processing
- Add TAESD support for GLM-Image (using f1 variant)
This commit is contained in:
CalamitousFelicitousness
2026-01-14 03:33:49 +00:00
parent 8500156888
commit 3f259cff9a
8 changed files with 151 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/sd_models.py
+4
View File
@@ -483,6 +483,10 @@ def load_diffuser_force(detected_model_type, checkpoint_info, diffusers_load_con
from pipelines.model_ovis import load_ovis
sd_model = load_ovis(checkpoint_info, diffusers_load_config)
allow_post_quant = False
elif model_type in ['GLM-Image']:
from pipelines.model_glm import load_glm_image
sd_model = load_glm_image(checkpoint_info, diffusers_load_config)
allow_post_quant = False
except Exception as e:
shared.log.error(f'Load {op}: path="{checkpoint_info.path}" {e}')
if debug_load: