9b52e24430
added dynamic chunking
2026-05-20 17:46:21 +03:00
b71a0742d5
Merge branch 'trellis2' of https://github.com/yousef-rafat/ComfyUI into pr/12183
2026-05-20 17:15:56 +03:00
f9a63ab2aa
remove triton, custom datatype, split mesh postpro
2026-05-20 17:15:33 +03:00
701b088e4a
Merge branch 'master' into trellis2
2026-05-20 10:56:30 +03:00
626b082838
Fix typo in ops.py ( #11925 )
2026-05-20 05:45:04 +08:00
a4382e056e
Use temporal downscale to make empty audio latent nodes more reusable. ( #13975 )
2026-05-19 00:14:30 -04:00
990a7ae7f2
Initial work to make downscale_ratio_temporal work. ( #13972 )
2026-05-18 23:01:43 -04:00
187e5237e1
Fix BiRefNet issue ( #13966 )
2026-05-19 05:03:22 +08:00
34d84369ad
bug fix in fill_holes
2026-05-18 23:15:00 +03:00
16f862f02a
implement dynamic clip saving ( #13959 )
...
Fix clip saving by doing the same patching process and diffusion
models.
2026-05-18 11:46:40 -07:00
971c9e3518
HiDream-O1: support area conditioning ( #13944 )
2026-05-18 01:17:05 -04:00
b39af210d0
Fix Qwen3.5 text generation with multiple input images ( #13943 )
2026-05-18 01:16:42 -04:00
f48d2a017e
Log which quant ops are enabled/emulated. ( #13946 )
2026-05-17 16:30:54 -04:00
4b97f54ff7
Merge branch 'master' into trellis2
2026-05-17 20:49:15 +08:00
bea4db2e02
remake
2026-05-16 19:49:51 +03:00
d3607a8e6d
feat: Add downscaled IC-LoRA support to LTXVAddGuide (CORE-102) ( #13896 )
2026-05-16 15:02:57 +08:00
5d5a4554e1
Remove useless option and clarify what lowvram does. ( #13922 )
2026-05-15 17:59:02 -07:00
9a1a5c3251
updates
2026-05-16 01:00:55 +03:00
33ce449c8b
Reduce LTX2.3 peak VRAM when guide_mask is in use (CORE-166) ( #13735 )
...
- Reduce peak VRAM by handling self_attn_mask more efficiently
- Fallback to SDPA when self_attention_mask is used
2026-05-16 00:02:27 +03:00
77e2ed5e01
feat: Support MoGe (CORE-168) ( #13878 )
2026-05-15 10:34:56 +08:00
84c276c895
package the trellis2 resolution
...
instead of taking it as an input from the user
2026-05-14 21:42:52 +03:00
6b7c00a33a
renaming
2026-05-14 20:30:14 +03:00
5a038c2ee1
Merge branch 'master' into trellis2
2026-05-14 14:52:16 +03:00
74c17a25e5
Fix void failing with RuntimeError: start (0) + length (464) exceeds dimension size (461). ( #13873 )
2026-05-13 12:37:30 -07:00
2bd65f2091
Better Hidream O1 mem usage factor for non dynamic vram. ( #13864 )
2026-05-12 20:55:38 -07:00
0155ddcbe3
Fix dtype issue with hidream o1 ( #13849 )
2026-05-11 20:53:13 -07:00
8e53f001a4
feat: Support HiDream-O1-Image (CORE-187) ( #13817 )
...
* Initial HiDream01-image support
* Cleanup nodes
* Cleaner handling of empty placeholder models
* Remove snap_to_predefined, prefer tooltip for the trained resolutions
* Add model and block wrappers
* Fix shift tooltip
* Add node to work around the patch tile issue
Experimental, runs multiple passes with the patch grid offset and blends with various different methods.
* Qwen35 vision rotary_pos_emb cast fix
* Fix embedding layout type
* Some small optimizations
* Cleanup, don't need this fallback
* Prefix KV cache, cleanup
Bit of speed, reduce redundant code
* Get rid of redundant custom sampler, refactor noise scaling
Our existing lcm sampler is mathematically same, just added the missing options to it instead and a node to control them. Refactored the noise scaling and fix it for the stochastic samplers, add a generic node to control the initial noise scale.
* Update nodes_hidream_o1.py
* Fix some cache validation cases
* Keep existing sampling params
* Remove redundant video vision path
* Replace some numpy ops with torch
* Fx RoPE index for batch size > 1
* Prefer torch preprocessing
* Rename block_type to be compatible with existing patch nodes
* Fixes and tweaks
2026-05-11 20:35:53 -07:00
0a7d2ffd68
Support anima TE lora kohya format. ( #13847 )
2026-05-11 20:01:52 -07:00
20e439419c
model_patcher: Fix safetensors saving of fp8 ( #13835 )
...
This was missing proper weight scale casting in the saving path.
2026-05-11 12:48:10 -07:00
f505cb4070
chore: remove extra word in comment ( #13826 )
2026-05-11 11:05:09 +08:00
3200f28e3a
Support Wan-Dancer ( #13813 )
...
* initial WanDancer support
* nodes_wandancer: Add list form of chunker.
Create an alternate list form of the node so the chunk gens can be
trivially looped by the comfy executor.
* Closer match to original soxr resampling
* Remove librosa node
* Cleanup
---------
Co-authored-by: Rattus <rattus128@gmail.com>
2026-05-09 14:02:56 -07:00
66669b2ded
I don't think there was any because nobody complained. ( #13807 )
2026-05-08 17:32:14 -07:00
17785619e8
.
2026-05-08 20:02:09 +03:00
25209d1b36
removing seeds from node display
2026-05-08 19:03:06 +03:00
c5ecd231a2
fix: Fix bug when mask not on same device (CORE-181) ( #13801 )
2026-05-08 23:06:29 +08:00
c05bff7ab8
Merge branch 'master' into trellis2
2026-05-08 14:50:49 +03:00
d3c18c1636
Add support for BiRefNet background remove model (CORE-46) ( #12747 )
2026-05-08 17:59:24 +08:00
bac6fc35fb
Fix typos ( #10986 )
2026-05-08 17:14:45 +08:00
ef8f25601a
Add I2V for causal forcing model. ( #13719 )
2026-05-07 18:38:36 -07:00
8dc3f3f209
Improve SAM3 large input handling ( #13767 )
2026-05-07 17:18:28 -07:00
ca150ba567
simplify and optimize model.forward
2026-05-07 18:47:03 +03:00
cd8c7a2306
Throttle dynamic VRAM prepare logging ( #13704 )
2026-05-07 10:41:13 +08:00
78b3096bf3
Void model - pass 1 & 2 (CORE-38) ( #13403 )
2026-05-05 19:59:04 -07:00
e5369c0eec
feat: Context windows - add causal_window_fix to improve blending of context windows (CORE-100) ( #13563 )
...
* Context windows: add causal_window_fix toggle
* Fix slice_cond to correctly handle causal anchor index for temporal offsets
2026-05-05 16:40:53 -07:00
1655f8089a
Add temporal_downscale_ratio to LatentFormat ( #13702 )
...
Co-authored-by: ozbayb <17261091+ozbayb@users.noreply.github.com>
Co-authored-by: Alexis Rolland <alexisrolland@hotmail.com>
Co-authored-by: Jukka Seppänen <40791699+kijai@users.noreply.github.com>
Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>
2026-05-05 16:30:00 -07:00
2f526f202b
Merge branch 'master' into trellis2
2026-05-05 23:20:05 +03:00
fed8d5efa6
feat: Auto-regressive video generation (CORE-25) ( #13082 )
2026-05-04 21:01:22 -07:00
e758594e3b
Add deploy environment header (Comfy-Env) to partner node API calls ( #13425 )
2026-05-04 20:17:56 -07:00
ae457da84b
feat: add generic --feature-flag CLI arg and --list-feature-flags registry ( #13685 )
2026-05-04 19:50:26 -07:00
1265955b34
ops: handle multi-compute of the same weight ( #13705 )
...
If the same weight is used multiple times within the same prefetch
window, it should only apply compute state mutations once. Mark the
weight as fully resident on the first pass accordingly.
2026-05-04 16:40:57 -07:00
Yousef Rafat
yy
comfyanonymous
rattus
Jukka Seppänen
Alexis Rolland
drozbay
Talmaj
box4wangjing
omahs
Jedrzej Kosinski