814 Commits

Author	SHA1	Message	Date
John Pollock	939ac7ebb4	Omit null batch_index from Trellis upsample output	2026-04-20 17:20:57 -05:00
John Pollock	90ebb50f00	Harden Trellis sparse latent seeding	2026-04-20 16:05:10 -05:00
John Pollock	0b99c8c44a	Fail loud on Trellis invalid batch metadata	2026-04-20 15:50:40 -05:00
John Pollock	a752dd4736	Harden Trellis sparse metadata validation	2026-04-20 14:46:23 -05:00
John Pollock	7d98cc1305	Fix Trellis seeded sparse batch semantics	2026-04-20 14:29:07 -05:00
John Pollock	49c1adeed6	Fix Trellis PR review regressions	2026-04-20 12:15:49 -05:00
John Pollock	c81ddf2349	Fix Trellis2 batched shape and texture semantics	2026-04-20 11:06:04 -05:00
John Pollock	9cfa8f2c01	Trellis2: inline batched mesh helpers	2026-04-19 23:47:57 -05:00
John Pollock	40219ab0fc	Trellis2: share batched mesh helpers	2026-04-19 23:33:09 -05:00
John Pollock	c297a9f839	Trellis2: handle empty and batched texture paint paths	2026-04-19 23:23:24 -05:00
John Pollock	6d99b636c1	Trellis2/Hunyuan3d: preserve mesh tensor contract in batch mode	2026-04-19 22:55:38 -05:00
John Pollock	44043ee6e5	Trellis2/Hunyuan3d: n>1 batched cascade support ... Mesh-producing nodes (VoxelToMeshBasic, VoxelToMesh, VaeDecodeShapeTrellis) previously stacked per-batch vertex/face tensors with torch.stack, which failed under batch>1 because per-item meshes have variable shapes. Store per-item tensors as lists when shapes differ; keep stacked-tensor fast path when shapes match. Update SaveGLB, PostProcessMesh, and VaeDecodeTextureTrellis consumers to iterate per-item when input is a list. Trellis2Conditioning.execute previously collapsed batched image/mask input to index 0, yielding identical conditioning for every batch item. Loop over the batch and produce per-image cond_512/cond_1024/neg_cond tensors stacked along the batch dim, matching the latent batch size. batch_size=1 behavior is unchanged. batch_size>1 runs now emit one GLB per batch item per SaveGLB node and carry per-image conditioning through the structure/shape/texture cascade.	2026-04-19 22:03:53 -05:00
John Pollock	7c6b237fe8	Match Copilot image_size restore pattern	2026-04-19 21:05:07 -05:00
John Pollock	2ad1ca5531	Handle missing Trellis2 image_size restore state	2026-04-19 20:51:22 -05:00
John Pollock	d7416e5690	Guard full Trellis2 conditioning image_size restore	2026-04-19 20:49:42 -05:00
John Pollock	04099ef605	Restore Trellis2 clip vision image_size state	2026-04-19 19:53:30 -05:00
Yousef R. Gamaleldin	e2171627c3	Merge branch 'master' into trellis2	2026-04-12 20:19:33 +02:00
Yousef Rafat	a1364a7b00	small final change	2026-04-12 20:14:47 +02:00
comfyanonymous	a2840e7552	Make ImageUpscaleWithModel node work with intermediate device and dtype. (#13357)	2026-04-10 21:48:26 -04:00
Jukka Seppänen	a134423890	SDPose: resize input always (#13349)	2026-04-10 11:26:55 -10:00
Yousef Rafat	243691c258	texture fixes	2026-04-10 19:18:14 +02:00
Yousef Rafat	937faafe21	corrected simplification logic	2026-04-10 16:33:19 +02:00
Yousef Rafat	4e14d42da1	comfy ops + color support in postprocess	2026-04-10 16:12:23 +02:00
Yousef Rafat	ea255543e6	structure generation works	2026-04-10 14:24:07 +02:00
Yousef Rafat	2cb06431e8	fix for conditioning	2026-04-07 23:02:33 +02:00
comfyanonymous	61c2387436	Ace step empty latent nodes follow intermediate dtype. (#13313)	2026-04-06 18:12:16 -07:00
Terry Jia	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
Yousef Rafat	57b306464e	texture generation works	2026-04-03 01:22:38 +02:00
Yousef Rafat	72640888ff	wrong normalization for the texture node	2026-03-30 23:20:46 +02:00
Christian Byrne	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 Seppänen	a500f1edac	CORE-13 feat: Support RT-DETRv4 detection model (#12748)	2026-03-28 23:34:10 -04:00
Terry Jia	3696c5bad6	Add has_intermediate_output flag for nodes with interactive UI (#13048)	2026-03-27 21:06:38 -04:00
Yousef Rafat	5559569735	..	2026-03-27 20:52:23 +02:00
comfyanonymous	b1fdbeb9a7	Fix blur and sharpen nodes not working with fp16 intermediates. (#13181)	2026-03-26 22:18:16 -04:00
Terry Jia	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 Seppänen	404d7b9978	feat: Support Qwen3.5 text generation models (#12771)	2026-03-25 22:48:28 -04:00
Dante	6580a6bc01	fix(number-convert): preserve int precision for large numbers (#13147)	2026-03-25 18:06:34 -04:00
Yousef Rafat	22dcd81fb3	fixed color addition	2026-03-25 23:51:54 +02:00
Yousef Rafat	d2c37c222a	pytorch -> scipy	2026-03-25 17:03:52 +02:00
Krishna Chaitanya	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
Yousef Rafat	fe25190cae	add color support for save mesh	2026-03-25 02:40:15 +02:00
Kohaku-Blueleaf	5ebb0c2e0b	FP8 bwd training (#13121)	2026-03-24 20:39:04 -04:00
Dante	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
Terry Jia	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
Yousef Rafat	56e52e5d03	work on txt gen	2026-03-24 02:44:03 +02:00
Jukka Seppänen	e87858e974	feat: LTX2: Support reference audio (ID-LoRA) (#13111)	2026-03-23 18:22:24 -04:00
comfyanonymous	a11f68dd3b	Fix canny node not working with fp16. (#13085)	2026-03-20 23:15:50 -04:00
Yousef Rafat	def8947e75	shape working	2026-03-20 18:37:11 +02:00
drozbay	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
Yousef Rafat	5d2548822c	.	2026-03-20 02:36:01 +02:00