* ops: introduce autopad for conv3d
This works around pytorch missing ability to causal pad as part of the
kernel and avoids massive weight duplications for padding.
* wan-vae: rework causal padding
This currently uses F.pad which takes a full deep copy and is liable to
be the VRAM peak. Instead, kick spatial padding back to the op and
consolidate the temporal padding with the cat for the cache.
* wan-vae: implement zero pad fast path
The WAN VAE is also QWEN where it is used single-image. These
convolutions are however zero padded 3d convolutions, which means the
VAE is actually just 2D down the last element of the conv weight in
the temporal dimension. Fast path this, to avoid adding zeros that
then just evaporate in convoluton math but cost computation.
* Disable timestep embed compression when inpainting
Spatial inpainting not compatible with the compression
* Reduce crossattn peak VRAM
* LTX2: Refactor forward function for better VRAM efficiency
- Add search_aliases for discoverability: resize, scale, dimensions, etc.
- Add node description for hover tooltip
- Add tooltips to all inputs explaining their behavior
- Reorder options: most common (scale dimensions) first, most technical (scale to multiple) last
Addresses user feedback that 'resize' search returned nothing useful and
options like 'match size' and 'scale to multiple' were not self-explanatory.
- Add search_aliases for discoverability: resize, scale, dimensions, etc.
- Add node description for hover tooltip
- Add tooltips to all inputs explaining their behavior
- Reorder options: most common (scale dimensions) first, most technical (scale to multiple) last
Addresses user feedback that 'resize' search returned nothing useful and
options like 'match size' and 'scale to multiple' were not self-explanatory.
* causal_video_ae: Remove attention ResNet
This attention_head_dim argument does not exist on this constructor so
this is dead code. Remove as generic attention mid VAE conflicts with
temporal roll.
* ltx-vae: consoldate causal/non-causal code paths
* ltx-vae: add cache rolling adder
* ltx-vae: use cached adder for resnet
* ltx-vae: Implement rolling VAE
Implement a temporal rolling VAE for the LTX2 VAE.
Usually when doing temporal rolling VAEs you can just chunk on time relying
on causality and cache behind you as you go. The LTX VAE is however
non-causal.
So go whole hog and implement per layer run ahead and backpressure between
the decoder layers using recursive state beween the layers.
Operations are ammended with temporal_cache_state{} which they can use to
hold any state then need for partial execution. Convolutions cache their
inputs behind the up to N-1 frames, and skip connections need to cache the
mismatch between convolution input and output that happens due to missing
future (non-causal) input.
Each call to run_up() processes a layer accross a range on input that
may or may not be complete. It goes depth first to process as much as
possible to try and digest frames to the final output ASAP. If layers run
out of input due to convolution losses, they simply return without action
effectively applying back-pressure to the earlier layers. As the earlier
layers do more work and caller deeper, the partial states are reconciled
and output continues to digest depth first as much as possible.
Chunking is done using a size quota rather than a fixed frame length and
any layer can initiate chunking, and multiple layers can chunk at different
granulatiries. This remove the old limitation of always having to process
1 latent frame to entirety and having to hold 8 full decoded frames as
the VRAM peak.
* re-init
* Update model_multitalk.py
* whitespace...
* Update model_multitalk.py
* remove print
* this is redundant
* remove import
* Restore preview functionality
* Move block_idx to transformer_options
* Remove LoopingSamplerCustomAdvanced
* Remove looping functionality, keep extension functionality
* Update model_multitalk.py
* Handle ref_attn_mask with separate patch to avoid having to always return q and k from self_attn
* Chunk attention map calculation for multiple speakers to reduce peak VRAM usage
* Update model_multitalk.py
* Add ModelPatch type back
* Fix for latest upstream
* Use DynamicCombo for cleaner node
Basically just so that single_speaker mode hides mask inputs and 2nd audio input
* Update nodes_wan.py
For LTX Audio VAE, remove normalization of audio during MEL spectrogram creation.
This aligs inference with training and prevents loud audio from being attenuated.
* In-progress autogrow validation fixes - properly looks at required/optional inputs, now working on the edge case that all inputs are optional and nothing is plugged in (should just be an empty dictionary passed into node)
* Allow autogrow to work with all inputs being optional
* Revert accidentally pushed changes to nodes_logic.py
Add 'advanced' boolean parameter to Input and WidgetInput base classes
and propagate to all typed Input subclasses (Boolean, Int, Float, String,
Combo, MultiCombo, Webcam, MultiType, MatchType, ImageCompare).
When set to True, the frontend will hide these inputs by default in a
collapsible 'Advanced Inputs' section in the right side panel, reducing
visual clutter for power-user options.
This enables nodes to expose advanced configuration options (like encoding
parameters, quality settings, etc.) without overwhelming typical users.
Frontend support: ComfyUI_frontend PR #7812
