Support for Qwen Diffsynth Controlnets canny and depth. (#9465)

These are not real controlnets but actually a patch on the model so they
will be treated as such.

Put them in the models/model_patches/ folder.

Use the new ModelPatchLoader and QwenImageDiffsynthControlnet nodes.
This commit is contained in:
comfyanonymous
2025-08-20 19:26:37 -07:00
committed by GitHub
parent e73a9dbe30
commit 0963493a9c
7 changed files with 184 additions and 1 deletions

View File

@@ -593,7 +593,13 @@ def load_models_gpu(models, memory_required=0, force_patch_weights=False, minimu
else:
minimum_memory_required = max(inference_memory, minimum_memory_required + extra_reserved_memory())
models = set(models)
models_temp = set()
for m in models:
models_temp.add(m)
for mm in m.model_patches_models():
models_temp.add(mm)
models = models_temp
models_to_load = []