mirror of
https://github.com/Comfy-Org/ComfyUI.git
synced 2026-09-09 02:26:31 +08:00
Merge master into worksplit-multigpu (#13546)
* fix: pin SQLAlchemy>=2.0 in requirements.txt (fixes #13036) (#13316) * Refactor io to IO in nodes_ace.py (#13485) * Bump comfyui-frontend-package to 1.42.12 (#13489) * Make the ltx audio vae more native. (#13486) * feat(api-nodes): add automatic downscaling of videos for ByteDance 2 nodes (#13465) * Support standalone LTXV audio VAEs (#13499) * [Partner Nodes] added 4K resolution for Veo models; added Veo 3 Lite model (#13330) * feat(api nodes): added 4K resolution for Veo models; added Veo 3 Lite model Signed-off-by: bigcat88 <bigcat88@icloud.com> * increase poll_interval from 5 to 9 --------- Signed-off-by: bigcat88 <bigcat88@icloud.com> Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com> * Bump comfyui-frontend-package to 1.42.14 (#13493) * Add gpt-image-2 as version option (#13501) * Allow logging in comfy app files. (#13505) * chore: update workflow templates to v0.9.59 (#13507) * fix(veo): reject 4K resolution for veo-3.0 models in Veo3VideoGenerationNode (#13504) The tooltip on the resolution input states that 4K is not available for veo-3.1-lite or veo-3.0 models, but the execute guard only rejected the lite combination. Selecting 4K with veo-3.0-generate-001 or veo-3.0-fast-generate-001 would fall through and hit the upstream API with an invalid request. Broaden the guard to match the documented behavior and update the error message accordingly. Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com> * feat: RIFE and FILM frame interpolation model support (CORE-29) (#13258) * initial RIFE support * Also support FILM * Better RAM usage, reduce FILM VRAM peak * Add model folder placeholder * Fix oom fallback frame loss * Remove torch.compile for now * Rename model input * Shorter input type name --------- * fix: use Parameter assignment for Stable_Zero123 cc_projection weights (fixes #13492) (#13518) On Windows with aimdo enabled, disable_weight_init.Linear uses lazy initialization that sets weight and bias to None to avoid unnecessary memory allocation. This caused a crash when copy_() was called on the None weight attribute in Stable_Zero123.__init__. Replace copy_() with direct torch.nn.Parameter assignment, which works correctly on both Windows (aimdo enabled) and other platforms. * Derive InterruptProcessingException from BaseException (#13523) * bump manager version to 4.2.1 (#13516) * ModelPatcherDynamic: force cast stray weights on comfy layers (#13487) the mixed_precision ops can have input_scale parameters that are used in tensor math but arent a weight or bias so dont get proper VRAM management. Treat these as force-castable parameters like the non comfy weight, random params are buffers already are. * Update logging level for invalid version format (#13526) * [Partner Nodes] add SD2 real human support (#13509) * feat(api-nodes): add SD2 real human support Signed-off-by: bigcat88 <bigcat88@icloud.com> * fix: add validation before uploading Assets Signed-off-by: bigcat88 <bigcat88@icloud.com> * Add asset_id and group_id displaying on the node Signed-off-by: bigcat88 <bigcat88@icloud.com> * extend poll_op to use instead of custom async cycle Signed-off-by: bigcat88 <bigcat88@icloud.com> * added the polling for the "Active" status after asset creation Signed-off-by: bigcat88 <bigcat88@icloud.com> * updated tooltip for group_id * allow usage of real human in the ByteDance2FirstLastFrame node * add reference count limits * corrected price in status when input assets contain video Signed-off-by: bigcat88 <bigcat88@icloud.com> --------- Signed-off-by: bigcat88 <bigcat88@icloud.com> * feat: SAM (segment anything) 3.1 support (CORE-34) (#13408) * [Partner Nodes] GPTImage: fix price badges, add new resolutions (#13519) * fix(api-nodes): fixed price badges, add new resolutions Signed-off-by: bigcat88 <bigcat88@icloud.com> * proper calculate the total run cost when "n > 1" Signed-off-by: bigcat88 <bigcat88@icloud.com> --------- Signed-off-by: bigcat88 <bigcat88@icloud.com> * chore: update workflow templates to v0.9.61 (#13533) * chore: update embedded docs to v0.4.4 (#13535) * add 4K resolution to Kling nodes (#13536) Signed-off-by: bigcat88 <bigcat88@icloud.com> * Fix LTXV Reference Audio node (#13531) * comfy-aimdo 0.2.14: Hotfix async allocator estimations (#13534) This was doing an over-estimate of VRAM used by the async allocator when lots of little small tensors were in play. Also change the versioning scheme to == so we can roll forward aimdo without worrying about stable regressions downstream in comfyUI core. * Disable sageattention for SAM3 (#13529) Causes Nans * execution: Add anti-cycle validation (#13169) Currently if the graph contains a cycle, the just inifitiate recursions, hits a catch all then throws a generic error against the output node that seeded the validation. Instead, fail the offending cycling mode chain and handlng it as an error in its own right. Co-authored-by: guill <jacob.e.segal@gmail.com> * chore: update workflow templates to v0.9.62 (#13539) --------- Signed-off-by: bigcat88 <bigcat88@icloud.com> Co-authored-by: Octopus <liyuan851277048@icloud.com> Co-authored-by: comfyanonymous <121283862+comfyanonymous@users.noreply.github.com> Co-authored-by: Comfy Org PR Bot <snomiao+comfy-pr@gmail.com> Co-authored-by: Alexander Piskun <13381981+bigcat88@users.noreply.github.com> Co-authored-by: Jukka Seppänen <40791699+kijai@users.noreply.github.com> Co-authored-by: AustinMroz <austin@comfy.org> Co-authored-by: Daxiong (Lin) <contact@comfyui-wiki.com> Co-authored-by: Matt Miller <matt@miller-media.com> Co-authored-by: blepping <157360029+blepping@users.noreply.github.com> Co-authored-by: Dr.Lt.Data <128333288+ltdrdata@users.noreply.github.com> Co-authored-by: rattus <46076784+rattus128@users.noreply.github.com> Co-authored-by: guill <jacob.e.segal@gmail.com>
This commit is contained in:
Jedrzej Kosinski
+11
-6
@@ -774,9 +774,9 @@ class ModelPatcher:
|
||||
sd.pop(k)
|
||||
return sd
|
||||
|
||||
def patch_weight_to_device(self, key, device_to=None, inplace_update=False, return_weight=False):
|
||||
def patch_weight_to_device(self, key, device_to=None, inplace_update=False, return_weight=False, force_cast=False):
|
||||
weight, set_func, convert_func = get_key_weight(self.model, key)
|
||||
if key not in self.patches:
|
||||
if key not in self.patches and not force_cast:
|
||||
return weight
|
||||
|
||||
inplace_update = self.weight_inplace_update or inplace_update
|
||||
@@ -784,7 +784,7 @@ class ModelPatcher:
|
||||
if key not in self.backup and not return_weight:
|
||||
self.backup[key] = collections.namedtuple('Dimension', ['weight', 'inplace_update'])(weight.to(device=self.offload_device, copy=inplace_update), inplace_update)
|
||||
|
||||
temp_dtype = comfy.model_management.lora_compute_dtype(device_to)
|
||||
temp_dtype = comfy.model_management.lora_compute_dtype(device_to) if key in self.patches else None
|
||||
if device_to is not None:
|
||||
temp_weight = comfy.model_management.cast_to_device(weight, device_to, temp_dtype, copy=True)
|
||||
else:
|
||||
@@ -792,9 +792,10 @@ class ModelPatcher:
|
||||
if convert_func is not None:
|
||||
temp_weight = convert_func(temp_weight, inplace=True)
|
||||
|
||||
out_weight = comfy.lora.calculate_weight(self.patches[key], temp_weight, key)
|
||||
out_weight = comfy.lora.calculate_weight(self.patches[key], temp_weight, key) if key in self.patches else temp_weight
|
||||
if set_func is None:
|
||||
out_weight = comfy.float.stochastic_rounding(out_weight, weight.dtype, seed=comfy.utils.string_to_seed(key))
|
||||
if key in self.patches:
|
||||
out_weight = comfy.float.stochastic_rounding(out_weight, weight.dtype, seed=comfy.utils.string_to_seed(key))
|
||||
if return_weight:
|
||||
return out_weight
|
||||
elif inplace_update:
|
||||
@@ -1705,7 +1706,7 @@ class ModelPatcherDynamic(ModelPatcher):
|
||||
key = key_param_name_to_key(n, param_key)
|
||||
if key in self.backup:
|
||||
comfy.utils.set_attr_param(self.model, key, self.backup[key].weight)
|
||||
self.patch_weight_to_device(key, device_to=device_to)
|
||||
self.patch_weight_to_device(key, device_to=device_to, force_cast=True)
|
||||
weight, _, _ = get_key_weight(self.model, key)
|
||||
if weight is not None:
|
||||
self.model.model_loaded_weight_memory += weight.numel() * weight.element_size()
|
||||
@@ -1730,6 +1731,10 @@ class ModelPatcherDynamic(ModelPatcher):
|
||||
m._v = vbar.alloc(v_weight_size)
|
||||
allocated_size += v_weight_size
|
||||
|
||||
for param in params:
|
||||
if param not in ("weight", "bias"):
|
||||
force_load_param(self, param, device_to)
|
||||
|
||||
else:
|
||||
for param in params:
|
||||
key = key_param_name_to_key(n, param)
|
||||
|
||||
Reference in New Issue
Block a user