5591 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
comfyanonymousandGitHub	3f77450ef1	Fix #13214 (#13216)	2026-03-28 22:35:59 -04:00
Terry JiaandGitHub	fc1fdf3389	fix: avoid nested sampler function calls in Color Curves shader (#13209)	2026-03-28 13:13:05 -04:00
rattusandGitHub	b353a7c863	Integrate RAM cache with model RAM management (#13173)	2026-03-27 21:34:16 -04:00
Terry JiaandGitHub	3696c5bad6	Add has_intermediate_output flag for nodes with interactive UI (#13048)	2026-03-27 21:06:38 -04:00
comfyanonymousandGitHub	3a56201da5	Allow flux conditioning without a pooled output. (#13198)	2026-03-27 20:36:26 -04:00
Alexander PiskunandGitHub	6a2cdb817d	fix(api-nodes-nanobana): raise error when not output image is present (#13167) ... Signed-off-by: bigcat88 <bigcat88@icloud.com>	2026-03-27 12:11:41 -07:00
ComfyUI WikiandGitHub	85b7495135	chore: update workflow templates to v0.9.39 (#13196)	2026-03-27 10:13:02 -07:00
Jin YiandGitHub	225c52f6a4	fix: register image/svg+xml MIME type for .svg files (#13186) ... The /view endpoint returns text/plain for .svg files on some platforms because Python's mimetypes module does not always include SVG by default. Explicitly register image/svg+xml so <img> tags can render SVGs correctly. Amp-Thread-ID: https://ampcode.com/threads/T-019d2da7-6a64-726a-af91-bd9c44e7f43c	2026-03-26 22:13:29 -07:00
comfyanonymousandGitHub	b1fdbeb9a7	Fix blur and sharpen nodes not working with fp16 intermediates. (#13181)	2026-03-26 22:18:16 -04:00
Terry JiaandGitHub	1dc64f3526	feat: add curve inputs and raise uniform limit for GLSL shader node (#13158) ... * feat: add curve inputs and raise uniform limit for GLSL shader node * allow arbitrary size for curve	2026-03-26 21:45:05 -04:00
ComfyUI WikiandGitHub	359559c913	chore: update workflow templates to v0.9.38 (#13176)	2026-03-26 12:07:38 -07:00
Alexander PiskunandGitHub	8165485a17	feat(api-nodes): added new Topaz model (#13175) ... Signed-off-by: bigcat88 <bigcat88@icloud.com>	2026-03-26 12:02:04 -07:00
Jukka SeppänenandGitHub	b0fd65e884	fix: regression in text generate with LTXAV model (#13170)	2026-03-26 09:55:05 -07:00
comfyanonymousandGitHub	2a1f402601	Make Qwen 8B work with TextGenerate node. (#13160)	2026-03-25 23:21:44 -04:00
Luke Mino-AltherrandGitHub	3eba2dcf2d	fix(assets): recognize temp directory in asset category resolution (#13159)	2026-03-25 19:59:59 -07:00
Jukka SeppänenandGitHub	404d7b9978	feat: Support Qwen3.5 text generation models (#12771)	2026-03-25 22:48:28 -04:00
DanteandGitHub	6580a6bc01	fix(number-convert): preserve int precision for large numbers (#13147)	2026-03-25 18:06:34 -04:00
Dr.Lt.DataandGitHub	3b15651bc6	bump manager version to 4.1 (#13156)	2026-03-25 16:49:29 -04:00
Alexander PiskunandGitHub	a55835f10c	fix(api-nodes): made Reve node price badges more precise (#13154) ... Signed-off-by: bigcat88 <bigcat88@icloud.com>	2026-03-25 11:05:49 -07:00
Krishna ChaitanyaandGitHub	b53b10ea61	Fix Train LoRA crash when training_dtype is "none" with bfloat16 LoRA weights (#13145) ... When training_dtype is set to "none" and the model's native dtype is float16, GradScaler was unconditionally enabled. However, GradScaler does not support bfloat16 gradients (only float16/float32), causing a NotImplementedError when lora_dtype is "bf16" (the default). Fix by only enabling GradScaler when LoRA parameters are not in bfloat16, since bfloat16 has the same exponent range as float32 and does not need gradient scaling to avoid underflow. Fixes #13124	2026-03-24 23:53:44 -04:00
Luke Mino-AltherrandGitHub	7d5534d8e5	feat(assets): register output files as assets after prompt execution (#12812)	2026-03-24 20:48:55 -07:00
Kohaku-BlueleafandGitHub	5ebb0c2e0b	FP8 bwd training (#13121)	2026-03-24 20:39:04 -04:00
DanteandGitHub	a0a64c679f	Add Number Convert node (#13041) ... * Add Number Convert node for unified numeric type conversion Consolidates fragmented IntToFloat/FloatToInt nodes (previously only available via third-party packs like ComfyMath, FillNodes, etc.) into a single core node. - Single input accepting INT, FLOAT, STRING, and BOOL types - Two outputs: FLOAT and INT - Conversion: bool→0/1, string→parsed number, float↔int standard cast - Follows Math Expression node patterns (comfy_api, io.Schema, etc.) Refs: COM-16925 * Register nodes_number_convert.py in extras_files list Without this entry in nodes.py, the Number Convert node file would not be discovered and loaded at startup. * Add isfinite guard, exception chaining, and unit tests for Number Convert node - Add math.isfinite() check to prevent int() crash on inf/nan string inputs - Use 'from None' for cleaner exception chaining on string parse failure - Add 21 unit tests covering all input types and error paths	2026-03-24 15:38:08 -07:00
3 people	8e73678dae	CURVE node (#12757) ... * CURVE node * remove curve to sigmas node * feat: add CurveInput ABC with MonotoneCubicCurve implementation (#12986) CurveInput is an abstract base class so future curve representations (bezier, LUT-based, analytical functions) can be added without breaking downstream nodes that type-check against CurveInput. MonotoneCubicCurve is the concrete implementation that: - Mirrors frontend createMonotoneInterpolator (curveUtils.ts) exactly - Pre-computes slopes as numpy arrays at construction time - Provides vectorised interp_array() using numpy for batch evaluation - interp() for single-value evaluation - to_lut() for generating lookup tables CurveEditor node wraps raw widget points in MonotoneCubicCurve. * linear curve * refactor: move CurveEditor to comfy_extras/nodes_curve.py with V3 schema * feat: add HISTOGRAM type and histogram support to CurveEditor * code improve --------- Co-authored-by: Christian Byrne <cbyrne@comfy.org>	2026-03-24 17:47:28 -04:00
comfyanonymousandGitHub	c2862b24af	Update templates package version. (#13141)	2026-03-24 17:36:12 -04:00
Alexander PiskunandGitHub	f9ec85f739	feat(api-nodes): update xAI Grok nodes (#13140)	2026-03-24 13:27:39 -07:00
3 people	2d5fd3f5dd	fix: set default values of Color Adjustment node to zero (#13084) ... Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-03-24 14:22:30 -04:00
comfyanonymousandGitHub	2d4970ff67	Update frontend version to 1.42.8 (#13126)	2026-03-23 20:43:41 -04:00
Jukka SeppänenandGitHub	e87858e974	feat: LTX2: Support reference audio (ID-LoRA) (#13111)	2026-03-23 18:22:24 -04:00
Dr.Lt.DataandGitHub	da6edb5a4e	bump manager version to 4.1b8 (#13108)	2026-03-23 12:59:21 -04:00
comfyanonymousandGitHub	6265a239f3	Add warning for users who disable dynamic vram. (#13113)	2026-03-22 18:46:18 -04:00
TalmajandGitHub	d49420b3c7	LongCat-Image edit (#13003)	2026-03-21 23:51:05 -04:00
comfyanonymous	ebf6b52e32	ComfyUI v0.18.1 v0.18.1	2026-03-21 22:32:16 -04:00
rattusandGitHub	25b6d1d629	wan: vae: Fix light/color change (#13101) ... There was an issue where the resample split was too early and dropped one of the rolling convolutions a frame early. This is most noticable as a lighting/color change between pixel frames 5->6 (latent 2->3), or as a lighting change between the first and last frame in an FLF wan flow.	2026-03-21 18:44:35 -04:00
comfyanonymousandGitHub	11c15d8832	Fix fp16 intermediates giving different results. (#13100)	2026-03-21 17:53:25 -04:00
comfyanonymousandGitHub	b5d32e6ad2	Fix sampling issue with fp16 intermediates. (#13099)	2026-03-21 17:47:42 -04:00
comfyanonymousandGitHub	a11f68dd3b	Fix canny node not working with fp16. (#13085)	2026-03-20 23:15:50 -04:00
comfyanonymous	dc719cde9c	ComfyUI version 0.18.0 v0.18.0	2026-03-20 20:09:15 -04:00
Jedrzej KosinskiandGitHub	87cda1fc25	Move inline comfy.context_windows imports to top-level in model_base.py (#13083) ... The recent PR that added resize_cond_for_context_window methods to model classes used inline 'import comfy.context_windows' in each method body. This moves that import to the top-level import section, replacing 4 duplicate inline imports with a single top-level one.	2026-03-20 20:03:42 -04:00
comfyanonymousandGitHub	45d5c83a30	Make EmptyImage node follow intermediate device/dtype. (#13079)	2026-03-20 16:08:26 -04:00
Alexander PiskunandGitHub	c646d211be	feat(api-nodes): add Quiver SVG nodes (#13047)	2026-03-20 12:23:16 -07:00
drozbayandGitHub	589228e671	Add slice_cond and per-model context window cond resizing (#12645) ... * Add slice_cond and per-model context window cond resizing * Fix cond_value.size() call in context window cond resizing * Expose additional advanced inputs for ContextWindowsManualNode Necessary for WanAnimate context windows workflow, which needs cond_retain_index_list = 0 to work properly with its reference input. ---------	2026-03-19 20:42:42 -07:00
3 people	e4455fd43a	[API Nodes] mark seedream-3-0-t2i and seedance-1-0-lite models as deprecated (#13060) ... * chore(api-nodes): mark seedream-3-0-t2i and seedance-1-0-lite models as deprecated * fix(api-nodes): fixed old regression in the ByteDanceImageReference node --------- Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-03-19 20:05:01 -07:00
rattusandGitHub	f49856af57	ltx: vae: Fix missing init variable (#13074) ... Forgot to push this ammendment. Previous test results apply to this.	2026-03-19 22:34:58 -04:00
rattusandGitHub	82b868a45a	Fix VRAM leak in tiler fallback in video VAEs (#13073) ... * sd: soft_empty_cache on tiler fallback This doesnt cost a lot and creates the expected VRAM reduction in resource monitors when you fallback to tiler. * wan: vae: Don't recursion in local fns (move run_up) Moved Decoder3d’s recursive run_up out of forward into a class method to avoid nested closure self-reference cycles. This avoids cyclic garbage that delays garbage of tensors which in turn delays VRAM release before tiled fallback. * ltx: vae: Don't recursion in local fns (move run_up) Mov the recursive run_up out of forward into a class method to avoid nested closure self-reference cycles. This avoids cyclic garbage that delays garbage of tensors which in turn delays VRAM release before tiled fallback.	2026-03-19 22:30:27 -04:00
comfyanonymousandGitHub	8458ae2686	Revert "fix: run text encoders on MPS GPU instead of CPU for Apple Silicon (#…" (#13070) ... This reverts commit b941913f1d.	2026-03-19 15:27:55 -04:00
Jukka SeppänenandGitHub	fd0261d2bc	Reduce tiled decode peak memory (#13050)	2026-03-19 13:29:34 -04:00
rattusandGitHub	ab14541ef7	memory: Add more exclusion criteria to pinned read (#13067)	2026-03-19 10:03:20 -07:00
rattusandGitHub	6589562ae3	ltx: vae: implement chunked encoder + CPU IO chunking (Big VRAM reductions) (#13062) ... * ltx: vae: add cache state to downsample block * ltx: vae: Add time stride awareness to causal_conv_3d * ltx: vae: Automate truncation for encoder Other VAEs just truncate without error. Do the same. * sd/ltx: Make chunked_io a flag in its own right Taking this bi-direcitonal, so make it a for-purpose named flag. * ltx: vae: implement chunked encoder + CPU IO chunking People are doing things with big frame counts in LTX including V2V flows. Implement the time-chunked encoder to keep the VRAM down, with the converse of the new CPU pre-allocation technique, where the chunks are brought from the CPU JIT. * ltx: vae-encode: round chunk sizes more strictly Only powers of 2 and multiple of 8 are valid due to cache slicing.	2026-03-19 10:01:12 -07:00
rattusandGitHub	fabed694a2	ltx: vae: implement chunked encoder + CPU IO chunking (Big VRAM reductions) (#13062) ... * ltx: vae: add cache state to downsample block * ltx: vae: Add time stride awareness to causal_conv_3d * ltx: vae: Automate truncation for encoder Other VAEs just truncate without error. Do the same. * sd/ltx: Make chunked_io a flag in its own right Taking this bi-direcitonal, so make it a for-purpose named flag. * ltx: vae: implement chunked encoder + CPU IO chunking People are doing things with big frame counts in LTX including V2V flows. Implement the time-chunked encoder to keep the VRAM down, with the converse of the new CPU pre-allocation technique, where the chunks are brought from the CPU JIT. * ltx: vae-encode: round chunk sizes more strictly Only powers of 2 and multiple of 8 are valid due to cache slicing.	2026-03-19 09:58:47 -07:00