efee285099
Add I2V for causal forcing model.
2026-05-05 20:55:51 +02:00
fc303cb2cf
Create a dedicated node for ar_sampler.
2026-05-05 20:55:51 +02:00
8ad8d101a1
Add better error handling for a custom ar_video sampler.
2026-05-05 20:55:51 +02:00
087844bd50
Base frame_seq_len on the padded token grid.
2026-05-05 20:55:51 +02:00
cac5120f96
Move KV cache end counter to Python int to avoid per-step host synchronization in AR sampling loops.
2026-05-05 20:55:51 +02:00
38514045ab
Remove ar_convert, now present in hg repackaged model repo.
2026-05-05 20:55:51 +02:00
f274674f14
Fix 'Process the tail block instead of truncating it', fix 'Don't mutate the patcher's shared transformer_options in place'.
2026-05-05 20:55:51 +02:00
a4377d588e
Remove dedicated ARLoader.
2026-05-05 20:55:51 +02:00
df7398a692
Refactor CausalWanModel to inherit from WanModel.
2026-05-05 20:55:51 +02:00
d1998480b0
Rewrite causual forcing using custom sampler with KSampler node.
2026-05-05 20:55:51 +02:00
92f937daa6
Apply ruff.
2026-05-05 20:55:51 +02:00
2aacf304fa
Rename causual forcing to using more general auto regressive naming convention.
2026-05-05 20:55:51 +02:00
bbce5a8c75
Fix CausalForcingSampler.
2026-05-05 20:55:51 +02:00
cbd2b17c67
Initial commit causual_forcing.
2026-05-05 20:55:51 +02:00
c33d26c283
fix: Proper memory estimation for frame interpolation when not using dynamic VRAM ( #13698 )
2026-05-04 20:20:40 +03:00
f3ea976cba
Fix a1111 typo in extra_model_paths.yaml ( #2720 )
2026-05-04 16:01:46 +08:00
5538f62b0b
fix: Update ColorTransfer node ref_image to be mandatory ( #13691 )
2026-05-04 12:33:11 +08:00
2806163f6e
Default control_after_generate to fixed in PrimitiveInt node ( #13690 )
2026-05-04 07:21:34 +08:00
cea8d0925f
Refactor LoadImageMask to use LoadImage code. ( #13687 )
2026-05-03 16:18:27 -04:00
b138133ffa
Enable triton comfy kitchen via cli-arg ( #12730 )
2026-05-03 14:07:21 -04:00
025e6792ee
Batch broadcasting in JoinImageWithAlpha node ( #13686 )
...
* Batch broadcasting in JoinImageWithAlpha node
2026-05-03 16:30:00 +03:00
867b8d2408
fix: gracefully handle port-in-use error on server startup ( #13001 )
...
Catch EADDRINUSE OSError when binding the TCP site and exit with a clear error message instead of an unhandled traceback.
2026-05-03 20:44:20 +08:00
d0f0b15cf5
Update ComfyUI screenshot in README ( #13683 )
...
Update ComfyUI screenshot to showcase a more modern workflow
2026-05-03 18:48:58 +08:00
b5bb83c964
Fix issue blend images with alpha ( #13615 )
...
Make ImageBlend and ImageCompositeMasked nodes handle images with different channel counts
2026-05-03 18:17:08 +08:00
f6d5068ac0
Update README ( #13679 )
...
Updated the README to include a new screenshot, improved description and add Ernie Image to supported models.
2026-05-03 12:20:17 +08:00
be95871adc
feat: Gemma4 text generation support (CORE-30) ( #13376 )
...
* initial gemma4 support
* parity with reference implementation
outputs can 100% match transformers with same sdpa flags, checkpoint this and then optimize
* Cleanup, video fixes
* cleanup, enable fused rms norm by default
* update comment
* Cleanup
* Update sd.py
* Various fixes
* Add fp8 scaled embedding support
* small fixes
* Translate think tokens
* Fix image encoder attention mask type
So it works with basic attention
* Handle thinking tokens different only for Gemma4
* Code cleanup
* Update nodes_textgen.py
* Use embed scale class instead of buffer
Slight difference to HF, but technically more accurate and simpler code
* Default to fused rms_norm
* Update gemma4.py
2026-05-02 22:46:15 -04:00
f756d801a1
[Partner Nodes] Topaz Astra 2 model ( #13672 )
...
* feat(api-nodes): add Topaz Astra 2 model
Signed-off-by: bigcat88 <bigcat88@icloud.com >
* feat(api-nodes): make Astra 2 the default Topaz upscaler model
Reorder UPSCALER_MODELS_MAP and the upscaler_model dynamic combo so
"Astra 2" appears first, surfacing it as the default selection.
---------
Signed-off-by: bigcat88 <bigcat88@icloud.com >
Co-authored-by: Marwan Mostafa <marawan206@gmail.com >
2026-05-02 19:29:00 -07:00
1d23a875ed
chore: update workflow templates to v0.9.68 ( #13678 )
2026-05-03 10:06:55 +08:00
ef6722f6be
Some cleanups to the load image node. ( #13677 )
2026-05-02 20:34:27 -04:00
783782d5d7
Implement block prefetch + Lora Async load + and adopt in LTX (Speedup!) (CORE-111) ( #13618 )
...
* mm: Use Aimdo raw allocator for cast buffers
pytorch manages allocation of growing buffers on streams poorly. Pyt
has no windows support for the expandable segments allocator (which is
the right tool for this job), while also segmenting the memory by
stream such that it can be generally re-used. So kick the problem to
aimdo which can just grow a virtual region thats freed per stream.
* plan
* ops: move cpu handler up to the caller
* ops: split up prefetch from weight prep block prefetching API
Split up the casting and weight formating/lora stuff in prep for
arbitrary prefetch support.
* ops: implement block prefetching API
allow a model to construct a prefetch list and operate it for increased
async offload.
* ltxv2: Implement block prefetching
* Implement lora async offload
Implement async offload of loras.
2026-05-02 19:23:24 -04:00
3e3ed8cc2a
Add script in AMD portable to launch with dynamic vram. ( #13667 )
2026-05-01 20:19:46 -04:00
67f6cb3527
List all the portable downloads in the README section. ( #13666 )
2026-05-01 20:19:32 -04:00
0230e0e7cc
Adding kijai ( #13664 )
...
Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com >
2026-05-02 06:37:18 +08:00
b5921c8ac2
SDPose: resize fix ( #13656 )
2026-05-01 14:17:25 -07:00
63103d519e
Remove IPEX and clean up checks and add missing synchronize during empty cache. ( #13653 )
2026-05-01 14:16:41 -07:00
cf758bd256
chore(api-nodes): increase default timeout for partner API node tasks ( #13663 )
...
Signed-off-by: bigcat88 <bigcat88@icloud.com >
Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com >
2026-05-01 12:48:41 -07:00
10b45a71cd
chore: update workflow templates to v0.9.66 ( #13662 )
...
Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com >
2026-05-01 12:11:30 -07:00
fa7553138e
chore(api-nodes): remove Moonvalley API nodes ( #13659 )
...
Signed-off-by: bigcat88 <bigcat88@icloud.com >
2026-05-01 11:09:25 -07:00
cf9cbec596
Reformat models variable into multiline array CORE-59 ( #13513 )
...
Co-authored-by: Talmaj Marinc <talmaj@comfy.org >
2026-05-01 17:20:11 +08:00
96f1cee9f5
chore(api-nodes): always display the custom width and height in GPTImage2 node ( #13651 )
...
Signed-off-by: bigcat88 <bigcat88@icloud.com >
2026-04-30 23:15:11 -07:00
97f58baaaf
Add alexisrolland and rattus128 as code owners ( #13648 )
2026-04-30 21:49:31 -04:00
e8e8fee224
chore: update workflow templates to v0.9.65 ( #13644 )
2026-04-30 18:14:28 -07:00
e9c311b245
OneTainer ERNIE LoRA support ( #13640 )
2026-04-30 19:33:41 -04:00
e6e0936128
Load other jpeg formats without taking so much memory. ( #13642 )
2026-04-30 19:33:09 -04:00
b633244635
[Partner Nodes] ByteDance: virtual portrait library for regular images ( #13638 )
...
* feat(api-nodes-bytedance): use the virtual portrait library for regular images
Signed-off-by: bigcat88 <bigcat88@icloud.com >
* fix: include shape in image dedup hash
Signed-off-by: bigcat88 <bigcat88@icloud.com >
---------
Signed-off-by: bigcat88 <bigcat88@icloud.com >
2026-04-30 11:49:08 -07:00
38ecad8f8a
feat(api-nodes): allow custom resolutions for GPTImage2 node ( #13631 )
...
Signed-off-by: bigcat88 <bigcat88@icloud.com >
2026-04-30 01:09:33 -07:00
a7d82baa06
Fix SQLAlchemy version format in requirements.txt ( #13547 )
...
Change SQLAlchemy>=2.0 to SQLAlchemy>=2.0.0 to satisfy the X.Y.Z
version format expected by install_util.is_valid_version().
2026-04-29 23:30:01 -04:00
d10fc2d652
Lower peak mem usage for 8 bit formats with pyav. ( #13626 )
2026-04-29 23:05:31 -04:00
a164c82913
Add high quality preview support for Flux2 latents ( #13496 )
2026-04-29 19:37:30 -04:00
5eeae3f1d8
Cogvideox ( #13402 )
...
---------
Co-authored-by: kijai <40791699+kijai@users.noreply.github.com >
Co-authored-by: Talmaj Marinc <talmaj@comfy.org >
2026-04-29 19:30:08 -04:00
