671 Commits

Author	SHA1	Message	Date
Jedrzej Kosinski	4691717340	Merge branch 'master' into seedvr2	2025-12-29 19:00:13 -08:00
Tavi Halperin	d7111e426a	ResizeByLongerSide: support video (#11555) ... (cherry picked from commit 98c6840aa4e5fd5407ba9ab113d209011e474bf6)	2025-12-29 17:07:29 -08:00
Alexander Piskun	eff4ea0b62	[V3] converted nodes_images.py to V3 schema (#11206) ... * converted nodes_images.py to V3 schema * fix test	2025-12-26 19:39:02 -08:00
Yousef Rafat	3039c7ba14	tile edge case handles by padding vid	2025-12-26 23:12:45 +02:00
Yousef Rafat	9b573da39b	added other types of attention + compatibility ... with images	2025-12-26 21:16:36 +02:00
Yousef Rafat	4d7012ecda	.	2025-12-26 02:23:51 +02:00
Yousef Rafat	21bc67d7db	final changes	2025-12-26 02:08:59 +02:00
comfyanonymous	532e285079	Add a ManualSigmas node. (#11499) ... Can be used to manually set the sigmas for a model. This node accepts a list of integer and floating point numbers separated with any non numeric character.	2025-12-24 19:09:37 -05:00
Yousef Rafat	7b2e5ef0af	outputs/speed/memory match custom node	2025-12-24 22:15:27 +02:00
Yousef Rafat	1afc2ed8e6	fixed the speed issue	2025-12-24 02:23:57 +02:00
Yousef Rafat	5b0c80a093	ruff	2025-12-23 12:35:00 +02:00
comfyanonymous	33aa808713	Make denoised output on custom sampler nodes work with nested tensors. (#11471)	2025-12-22 16:43:24 -05:00
Yousef Rafat	e30298dda2	..	2025-12-22 21:49:48 +02:00
Yousef Rafat	98b6bfcb71	revert file perm.	2025-12-22 21:46:40 +02:00
Yousef Rafat	5db5da790f	remove cfg cutoff node	2025-12-22 21:15:12 +02:00
Yousef Rafat	a4e9d071e8	video works	2025-12-22 18:12:46 +02:00
comfyanonymous	91bf6b6aa3	Add node to create empty latents for qwen image layered model. (#11460)	2025-12-21 19:59:40 -05:00
Yousef Rafat	4fe772fae9	improvements	2025-12-20 23:20:45 +02:00
rattus	767ee30f21	ZImageFunControlNet: Fix mask concatenation in --gpu-only (#11421) ... This operation trades in latents which in --gpu-only may be out of the GPU The two VAE results will follow the --gpu-only defined behaviour so follow the inpaint image device when calculating the mask in this path.	2025-12-20 00:22:17 -05:00
Yousef Rafat	0d2044a778	...	2025-12-19 20:28:09 +02:00
comfyanonymous	894802b0f9	Add LatentCutToBatch node. (#11411)	2025-12-18 22:21:40 -05:00
Yousef Rafat	74621b9d86	.	2025-12-18 14:52:10 +02:00
Yousef Rafat	db74a27870	fix vae issue	2025-12-18 14:13:41 +02:00
comfyanonymous	bf7dc63bd6	skip_load_model -> force_full_load (#11390) ... This should be a bit more clear and less prone to potential breakage if the logic of the load models changes a bit.	2025-12-17 23:29:32 -05:00
Kohaku-Blueleaf	86dbb89fc9	Resolution bucketing and Trainer implementation refactoring (#11117)	2025-12-17 22:15:27 -05:00
Yousef Rafat	acb9a11c6f	Merge branch 'seedvr2' of https://github.com/yousef-rafat/ComfyUI into seedvr2	2025-12-18 00:37:32 +02:00
Yousef Rafat	d9f71da998	works	2025-12-18 00:32:14 +02:00
chaObserv	827bb1512b	Add exp_heun_2_x0 sampler series (#11360)	2025-12-16 23:35:43 -05:00
Yousef R. Gamaleldin	183b377588	Merge branch 'master' into seedvr2	2025-12-17 00:39:06 +02:00
comfyanonymous	645ee1881e	Inpainting for z image fun control. Use the ZImageFunControlnet node. (#11346) ... image -> control image ex: pose inpaint_image -> image for inpainting mask -> inpaint mask	2025-12-15 23:38:12 -05:00
comfyanonymous	41bcf0619d	Add code to detect if a z image fun controlnet is broken or not. (#11341)	2025-12-15 20:51:06 -05:00
comfyanonymous	70541d4e77	Support the new qwen edit 2511 reference method. (#11340) ... index_timestep_zero can be selected in the FluxKontextMultiReferenceLatentMethod now with the display name set to the more generic "Edit Model Reference Method" node.	2025-12-15 19:20:34 -05:00
comfyanonymous	5cb1e0c9a0	Disable guards on transformer_options when torch.compile (#11317)	2025-12-15 16:49:29 -05:00
chaObserv	6592bffc60	seeds_2: add phi_2 variant and sampler node (#11309) ... * Add phi_2 solver type to seeds_2 * Add sampler node of seeds_2	2025-12-14 00:03:29 -05:00
Yousef Rafat	58e7cea796	lora, 7b model, cfg	2025-12-13 19:48:57 +02:00
comfyanonymous	da2bfb5b0a	Basic implementation of z image fun control union 2.0 (#11304) ... The inpaint part is currently missing and will be implemented later. I think they messed up this model pretty bad. They added some control_noise_refiner blocks but don't actually use them. There is a typo in their code so instead of doing control_noise_refiner -> control_layers it runs the whole control_layers twice. Unfortunately they trained with this typo so the model works but is kind of slow and would probably perform a lot better if they corrected their code and trained it again.	2025-12-13 01:39:11 -05:00
Yousef Rafat	768c9cedf8	..	2025-12-12 20:51:40 +02:00
Jukka Seppänen	982876d59a	WanMove support (#11247)	2025-12-11 22:29:34 -05:00
Yousef Rafat	d629c8f910	testing	2025-12-12 00:46:23 +02:00
Yousef Rafat	413ee3f687	.	2025-12-10 22:58:53 +02:00
Yousef Rafat	d12702ee0b	fixed some issues	2025-12-09 23:54:56 +02:00
Yousef Rafat	f030b3afc8	mostly fixing mistakes	2025-12-09 00:16:17 +02:00
Alexander Piskun	85c4b4ae26	chore: replace imports of deprecated V1 classes (#11127)	2025-12-08 01:27:02 -08:00
Yousef Rafat	4b9332cc21	continue building nodes / testing vae	2025-12-07 21:41:14 +02:00
Yousef Rafat	041dbd6a8a	add nodes	2025-12-07 01:00:08 +02:00
Jukka Seppänen	7ac7d69d94	Fix EmptyAudio node input types (#11149)	2025-12-06 10:09:44 -08:00
Alexander Piskun	913f86b727	[V3] convert nodes_mask.py to V3 schema (#10669) ... * convert nodes_mask.py to V3 schema * set "Preview Mask" as display name for MaskPreview	2025-12-05 20:24:10 -08:00
Alexander Piskun	117bf3f2bd	convert nodes_freelunch.py to the V3 schema (#10904)	2025-12-05 20:22:02 -08:00
Jukka Seppänen	fd109325db	Kandinsky5 model support (#10988) ... * Add Kandinsky5 model support lite and pro T2V tested to work * Update kandinsky5.py * Fix fp8 * Fix fp8_scaled text encoder * Add transformer_options for attention * Code cleanup, optimizations, use fp32 for all layers originally at fp32 * ImageToVideo -node * Fix I2V, add necessary latent post process nodes * Support text to image model * Support block replace patches (SLG mostly) * Support official LoRAs * Don't scale RoPE for lite model as that just doesn't work... * Update supported_models.py * Rever RoPE scaling to simpler one * Fix typo * Handle latent dim difference for image model in the VAE instead * Add node to use different prompts for clip_l and qwen25_7b * Reduce peak VRAM usage a bit * Further reduce peak VRAM consumption by chunking ffn * Update chunking * Update memory_usage_factor * Code cleanup, don't force the fp32 layers as it has minimal effect * Allow for stronger changes with first frames normalization Default values are too weak for any meaningful changes, these should probably be exposed as advanced node options when that's available. * Add image model's own chat template, remove unused image2video template * Remove hard error in ReplaceVideoLatentFrames -node * Update kandinsky5.py * Update supported_models.py * Fix typos in prompt template They were now fixed in the original repository as well * Update ReplaceVideoLatentFrames Add tooltips Make source optional Better handle negative index * Rename NormalizeVideoLatentFrames -node For bit better clarity what it does * Fix NormalizeVideoLatentStart node out on non-op	2025-12-05 22:20:22 -05:00
Jukka Seppänen	79d17ba233	Context windows fixes and features (#10975) ... * Apply cond slice fix * Add FreeNoise * Update context_windows.py * Add option to retain condition by indexes for each window This allows for example Wan/HunyuanVideo image to video to "work" by using the initial start frame for each window, otherwise windows beyond first will be pure T2V generations. * Update context_windows.py * Allow splitting multiple conds into different windows * Add handling for audio_embed * whitespace * Allow freenoise to work on other dims, handle 4D batch timestep Refactor Freenoise function. And fix batch handling as timesteps seem to be expanded to batch size now. * Disable experimental options for now So that the Freenoise and bugfixes can be merged first --------- Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com> Co-authored-by: ozbayb <17261091+ozbayb@users.noreply.github.com>	2025-12-05 12:42:46 -08:00