github/ai-toolkit
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Add support for fine-tuning Hidream O1 (#831)

Browse Source 
* Initial support for hidream. Lora keys likely need work

* Fix saving for hidream-o1

* Remove dependence on flash attention for hidream o1

* Fix gradient checkpointing for hidream o1

* A lot of fixes for hidream. Handle loading and saving as comfy model.

* Omit layers not used in comfy. Fix issue with lora loading keys in comfy

* Version bumpo
This commit is contained in:
Jaret Burkett (Ostris)
2026-05-12 11:15:16 -06:00
committed by GitHub
parent f38de2a2fe
commit fc4d6ebf39
14 changed files with 3633 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
extensions_built_in/diffusion_models/hidream/__init__.py
View File

@@ -1,2 +1,3 @@
from .hidream_model import HidreamModel
from .hidream_e1_model import HidreamE1Model
from .hidream_e1_model import HidreamE1Model
from .hidream_o1_model import HidreamO1Model