870 Commits

Include renames

Author	SHA1	Message	Date
drozbayandGitHub	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
drozbayandGitHub	41d73ad180	fix(audio): drop sample_rate key from LTXVEmptyLatentAudio (CORE-157) (#13716)	2026-05-05 11:33:16 -07:00
Alexis RollandandGitHub	639f631a08	chore: Update display names and categories for text nodes (CORE-155) (#13712)	2026-05-05 22:31:24 +08:00
Alvin TangandGitHub	8d75211300	fix: SplitImageToTileList and ImageMergeTileList to use tile_height for vertical stride minimum (#12882)	2026-05-05 20:29:11 +08:00
TalmajandGitHub	fed8d5efa6	feat: Auto-regressive video generation (CORE-25) (#13082)	2026-05-04 21:01:22 -07:00
Alexis RollandandGitHub	15a4494a4e	chore: Update display names and categories (CORE-151) (#13693) ... * Standardize DEPRECATED label in node display name * Promote category image/video to root level video/ * Update images and masks names and categories	2026-05-04 17:37:25 -07:00
Jukka SeppänenandGitHub	c33d26c283	fix: Proper memory estimation for frame interpolation when not using dynamic VRAM (#13698)	2026-05-04 20:20:40 +03:00
Alexis RollandandGitHub	5538f62b0b	fix: Update ColorTransfer node ref_image to be mandatory (#13691)	2026-05-04 12:33:11 +08:00
Jedrzej KosinskiandGitHub	2806163f6e	Default control_after_generate to fixed in PrimitiveInt node (#13690)	2026-05-04 07:21:34 +08:00
Jukka SeppänenandGitHub	025e6792ee	Batch broadcasting in JoinImageWithAlpha node (#13686) ... * Batch broadcasting in JoinImageWithAlpha node	2026-05-03 16:30:00 +03:00
Jukka SeppänenandGitHub	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
Jukka SeppänenandGitHub	b5921c8ac2	SDPose: resize fix (#13656)	2026-05-01 14:17:25 -07:00
4 people	24de8dc01b	Fix SolidMask and MaskComposite device mismatch with --gpu-only (#13296) ... SolidMask had a hardcoded device="cpu" while other nodes (e.g. EmptyImage) follow intermediate_device(). This causes a RuntimeError when MaskComposite combines masks from different device sources under --gpu-only. - SolidMask: use intermediate_device() instead of hardcoded "cpu" - MaskComposite: align source device to destination before operating Co-authored-by: Alexis Rolland <alexisrolland@hotmail.com> Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-04-28 01:18:19 -07:00
Daxiong (Lin)andGitHub	c0d77a5d53	Change the save 3d model node's filename prefix to 3d/ComfyUI (CORE-106) (#12826) ... * Change save 3d model's filename prefix to 3d/ComfyUI As this node has already changed from `Save GLB` to `Save 3D Model`, using the filename prefix `3d` will be better than `mesh` * use lowercase ---------	2026-04-28 00:59:59 -07:00
comfyanonymousandGitHub	115f418b64	Make EmptySD3LatentImage node use intermediate dtype. (#13577)	2026-04-26 23:23:57 -04:00
comfyanonymousandGitHub	c5d9edacd0	Print more tensor values in the preview any node. (#13544)	2026-04-23 22:19:00 -04:00
Jukka SeppänenandGitHub	6fbb6b6f49	Fix LTXV Reference Audio node (#13531)	2026-04-23 11:13:17 -07:00
Jukka SeppänenandGitHub	749d5b4e8d	feat: SAM (segment anything) 3.1 support (CORE-34) (#13408)	2026-04-23 00:07:43 -04:00
Jukka SeppänenandGitHub	db85cf03ff	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 ---------	2026-04-22 04:16:02 -07:00
comfyanonymousandGitHub	ad94d47221	Make the ltx audio vae more native. (#13486)	2026-04-21 11:02:42 -04:00
comfyanonymousandGitHub	c514890325	Refactor io to IO in nodes_ace.py (#13485)	2026-04-20 21:59:26 -04:00
Jukka SeppänenandGitHub	b9dedea57d	feat: SUPIR model support (CORE-17) (#13250)	2026-04-18 23:02:01 -04:00
rattusandGitHub	05f7531148	nodes_textgen: Implement use_default_template for LTX (#13451)	2026-04-17 12:20:09 -04:00
comfyanonymousandGitHub	1391579c33	Add JsonExtractString node. (#13435)	2026-04-17 00:20:16 -04:00
comfyanonymousandGitHub	e9a2d1e4cc	Add a way to disable default template in text gen node. (#13424)	2026-04-15 22:59:08 -04:00
comfyanonymousandGitHub	c5569e8627	Add string output to preview text node. (#13406)	2026-04-14 14:42:23 -04:00
comfyanonymousandGitHub	a2840e7552	Make ImageUpscaleWithModel node work with intermediate device and dtype. (#13357)	2026-04-10 21:48:26 -04:00
Jukka SeppänenandGitHub	a134423890	SDPose: resize input always (#13349)	2026-04-10 11:26:55 -10:00
comfyanonymousandGitHub	61c2387436	Ace step empty latent nodes follow intermediate dtype. (#13313)	2026-04-06 18:12:16 -07:00
3 people	7083484a48	image histogram node (#13153) ... * image histogram node * update color curve blueprint using image histogram node --------- Co-authored-by: guill <jacob.e.segal@gmail.com>	2026-04-06 14:54:02 -07:00
Christian ByrneandGitHub	55e6478526	Rename utils/string nodes with Text prefix and add search aliases (#13227) ... Rename all 11 nodes in the utils/string category to include a "Text" prefix for better discoverability and natural sorting. Regex nodes get user-friendly names without "Regex" in the display name. Renames: - Concatenate → Text Concatenate - Substring → Text Substring - Length → Text Length - Case Converter → Text Case Converter - Trim → Text Trim - Replace → Text Replace - Contains → Text Contains - Compare → Text Compare - Regex Match → Text Match - Regex Extract → Text Extract Substring - Regex Replace → Text Replace (Regex) All renamed nodes include their old display name as a search alias so users can still find them by searching the original name. Regex nodes also include "regex" as a search alias.	2026-03-29 21:02:44 -07:00
Jukka SeppänenandGitHub	a500f1edac	CORE-13 feat: Support RT-DETRv4 detection model (#12748)	2026-03-28 23:34:10 -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	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
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
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
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
Jukka SeppänenandGitHub	e87858e974	feat: LTX2: Support reference audio (ID-LoRA) (#13111)	2026-03-23 18:22:24 -04:00
comfyanonymousandGitHub	a11f68dd3b	Fix canny node not working with fp16. (#13085)	2026-03-20 23:15:50 -04:00
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
Kohaku-BlueleafandGitHub	20561aa919	[Trainer] FP4, 8, 16 training by native dtype support and quant linear autograd function (#12681)	2026-03-16 21:31:50 -04:00
3 people	593be209a4	feat: add essentials_category to nodes and blueprints for Essentials tab (#12573) ... * feat: add essentials_category to nodes and blueprints for Essentials tab Add ESSENTIALS_CATEGORY or essentials_category to 12 node classes and all 36 blueprint JSONs. Update SubgraphEntry TypedDict and subgraph_manager to extract and pass through the field. Fixes COM-15221 Amp-Thread-ID: https://ampcode.com/threads/T-019c83de-f7ab-7779-a451-0ba5940b56a9 * fix: import NotRequired from typing_extensions for Python 3.10 compat * refactor: keep only node class ESSENTIALS_CATEGORY, remove blueprint/subgraph changes Frontend will own blueprint categorization separately. * fix: remove essentials_category from CreateVideo (not in spec) --------- Co-authored-by: guill <jacob.e.segal@gmail.com>	2026-03-15 16:18:04 -07:00
comfyanonymousandGitHub	47e1e316c5	Lower kv cache memory usage. (#12909)	2026-03-12 16:54:38 -04:00
3 people	73d9599495	add painter node (#12294) ... * add painter node * use io.Color * code improve --------- Co-authored-by: guill <jacob.e.segal@gmail.com>	2026-03-12 09:55:29 -07:00
comfyanonymousandGitHub	44f1246c89	Support flux 2 klein kv cache model: Use the FluxKVCache node. (#12905)	2026-03-12 11:30:50 -04:00
rattusandGitHub	535c16ce6e	Widen OOM_EXCEPTION to AcceleratorError form (#12835) ... Pytorch only filters for OOMs in its own allocators however there are paths that can OOM on allocators made outside the pytorch allocators. These manifest as an AllocatorError as pytorch does not have universal error translation to its OOM type on exception. Handle it. A log I have for this also shows a double report of the error async, so call the async discarder to cleanup and make these OOMs look like OOMs.	2026-03-10 00:41:02 -04:00