andreas/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Enable Runtime Selection of Attention Functions (#9639)

Browse Source 
* Looking into a @wrap_attn decorator to look for 'optimized_attention_override' entry in transformer_options

* Created logging code for this branch so that it can be used to track down all the code paths where transformer_options would need to be added

* Fix memory usage issue with inspect

* Made WAN attention receive transformer_options, test node added to wan to test out attention override later

* Added **kwargs to all attention functions so transformer_options could potentially be passed through

* Make sure wrap_attn doesn't make itself recurse infinitely, attempt to load SageAttention and FlashAttention if not enabled so that they can be marked as available or not, create registry for available attention

* Turn off attention logging for now, make AttentionOverrideTestNode have a dropdown with available attention (this is a test node only)

* Make flux work with optimized_attention_override

* Add logs to verify optimized_attention_override is passed all the way into attention function

* Make Qwen work with optimized_attention_override

* Made hidream work with optimized_attention_override

* Made wan patches_replace work with optimized_attention_override

* Made SD3 work with optimized_attention_override

* Made HunyuanVideo work with optimized_attention_override

* Made Mochi work with optimized_attention_override

* Made LTX work with optimized_attention_override

* Made StableAudio work with optimized_attention_override

* Made optimized_attention_override work with ACE Step

* Made Hunyuan3D work with optimized_attention_override

* Make CosmosPredict2 work with optimized_attention_override

* Made CosmosVideo work with optimized_attention_override

* Made Omnigen 2 work with optimized_attention_override

* Made StableCascade work with optimized_attention_override

* Made AuraFlow work with optimized_attention_override

* Made Lumina work with optimized_attention_override

* Made Chroma work with optimized_attention_override

* Made SVD work with optimized_attention_override

* Fix WanI2VCrossAttention so that it expects to receive transformer_options

* Fixed Wan2.1 Fun Camera transformer_options passthrough

* Fixed WAN 2.1 VACE transformer_options passthrough

* Add optimized to get_attention_function

* Disable attention logs for now

* Remove attention logging code

* Remove _register_core_attention_functions, as we wouldn't want someone to call that, just in case

* Satisfy ruff

* Remove AttentionOverrideTest node, that's something to cook up for later
This commit is contained in:
Jedrzej Kosinski
2025-09-12 15:07:38 -07:00
committed by GitHub
parent b149e2e1e3
commit d7f40442f9
26 changed files with 316 additions and 179 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
comfy/ldm/chroma/model.py
View File

@@ -193,14 +193,16 @@ class Chroma(nn.Module):
txt=args["txt"],
vec=args["vec"],
pe=args["pe"],
attn_mask=args.get("attn_mask"))
attn_mask=args.get("attn_mask"),
transformer_options=args.get("transformer_options"))
return out
out = blocks_replace[("double_block", i)]({"img": img,
"txt": txt,
"vec": double_mod,
"pe": pe,
"attn_mask": attn_mask},
"attn_mask": attn_mask,
"transformer_options": transformer_options},
{"original_block": block_wrap})
txt = out["txt"]
img = out["img"]
@@ -209,7 +211,8 @@ class Chroma(nn.Module):
txt=txt,
vec=double_mod,
pe=pe,
attn_mask=attn_mask)
attn_mask=attn_mask,
transformer_options=transformer_options)
if control is not None: # Controlnet
control_i = control.get("input")
@@ -229,17 +232,19 @@ class Chroma(nn.Module):
out["img"] = block(args["img"],
vec=args["vec"],
pe=args["pe"],
attn_mask=args.get("attn_mask"))
attn_mask=args.get("attn_mask"),
transformer_options=args.get("transformer_options"))
return out
out = blocks_replace[("single_block", i)]({"img": img,
"vec": single_mod,
"pe": pe,
"attn_mask": attn_mask},
"attn_mask": attn_mask,
"transformer_options": transformer_options},
{"original_block": block_wrap})
img = out["img"]
else:
img = block(img, vec=single_mod, pe=pe, attn_mask=attn_mask)
img = block(img, vec=single_mod, pe=pe, attn_mask=attn_mask, transformer_options=transformer_options)
if control is not None: # Controlnet
control_o = control.get("output")