2211 Commits

Author	SHA1	Message	Date
rattus	1cf23b969e	Merge 3f717816e1 into fb51a988b6	2026-05-13 16:41:56 -10:00
Talmaj	74c17a25e5	Fix void failing with RuntimeError: start (0) + length (464) exceeds dimension size (461). (#13873)	2026-05-13 12:37:30 -07:00
Rattus	3f717816e1	execution: implement pin eviction on RAM presure ... Add back proper pin freeing on RAM pressure	2026-05-13 22:23:54 +10:00
Rattus	d61026d020	pins: implement freeing intermediate for pinned memory ... Pinning is more important than inactive intermediates and the stream pin buffer is more important than even active intermediates.	2026-05-13 22:23:54 +10:00
Rattus	ee927aafa8	ops: sync the CPU with only the offload stream activity ... This was syncing with the offload stream which itself is synced with the compute stream, so this was syncing CPU with compute transitively. Define the event to sync it more gently.	2026-05-13 22:23:54 +10:00
comfyanonymous	2bd65f2091	Better Hidream O1 mem usage factor for non dynamic vram. (#13864)	2026-05-12 20:55:38 -07:00
comfyanonymous	0155ddcbe3	Fix dtype issue with hidream o1 (#13849)	2026-05-11 20:53:13 -07:00
Jukka Seppänen	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
comfyanonymous	0a7d2ffd68	Support anima TE lora kohya format. (#13847)	2026-05-11 20:01:52 -07:00
Rattus	44c0a0602b	ops: remove unused arg ... This was defeatured in aimdo iteration	2026-05-12 11:04:59 +10:00
Rattus	3a3b75a7e3	implement pinned loras	2026-05-12 11:04:59 +10:00
Rattus	e48dace145	prepare for multiple pin sets	2026-05-12 11:04:59 +10:00
Rattus	8e473d756f	lora: re-implement as inplace swiss-army-knife operation	2026-05-12 11:04:59 +10:00
Rattus	2b927e1783	LowVRAMPatch: change to two-phase visit	2026-05-12 11:04:59 +10:00
Rattus	8187cd783e	Implement JIT pinned memory pressure ... Replace the predictive pin pressure mechanism with JIT PIN memory pressure.	2026-05-12 11:04:59 +10:00
Rattus	17955235b2	remove old pin path	2026-05-12 11:04:59 +10:00
Rattus	8070cb7780	Add stream host pin buffer for AIMDO casts ... Introduce per-offload-stream HostBuffer reuse for pinned staging, include it in cast buffer reset synchronization. Defer actual casts that go via this pin path to a separate pass such that the buffer can be allocated monolithically (to avoid cudaHostRegister thrash).	2026-05-12 11:04:59 +10:00
Rattus	b66b642068	mm: use aimdo to do transfer from disk to pin ... Aimdo implements a faster threaded loader.	2026-05-12 11:04:59 +10:00
Rattus	157965a1c9	pinned_memory: implement with aimdo growable buffer ... Use a single growable buffer so we can do threaded pre-warming on pinned memory.	2026-05-12 11:04:59 +10:00
Rattus	1fe3a13f84	model_management: disable non-dynamic smart memory ... Disable smart memory outright for non dynamic models. This is a minor step towards deprecation of --disable-dynamic-vram and the legacy ModelPatcher. This is needed for estimate-free model development, where new models can opt-out of supplying a memory estimate and not have to worry about hard VRAM allocations due to legacy non-dynamic model patchers This is also a general stability increase for a lot of stray use cases where estimates may still be off and going forward we are not going to accurately maintain such estimates.	2026-05-12 11:04:59 +10:00
rattus	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
box4wangjing	f505cb4070	chore: remove extra word in comment (#13826)	2026-05-11 11:05:09 +08:00
Jukka Seppänen	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
comfyanonymous	66669b2ded	I don't think there was any because nobody complained. (#13807)	2026-05-08 17:32:14 -07:00
Alexis Rolland	c5ecd231a2	fix: Fix bug when mask not on same device (CORE-181) (#13801)	2026-05-08 23:06:29 +08:00
Yousef R. Gamaleldin	d3c18c1636	Add support for BiRefNet background remove model (CORE-46) (#12747)	2026-05-08 17:59:24 +08:00
omahs	bac6fc35fb	Fix typos (#10986)	2026-05-08 17:14:45 +08:00
Talmaj	ef8f25601a	Add I2V for causal forcing model. (#13719)	2026-05-07 18:38:36 -07:00
Jukka Seppänen	8dc3f3f209	Improve SAM3 large input handling (#13767)	2026-05-07 17:18:28 -07:00
Jukka Seppänen	cd8c7a2306	Throttle dynamic VRAM prepare logging (#13704)	2026-05-07 10:41:13 +08:00
Talmaj	78b3096bf3	Void model - pass 1 & 2 (CORE-38) (#13403)	2026-05-05 19:59:04 -07:00
drozbay	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
drozbay	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
Talmaj	fed8d5efa6	feat: Auto-regressive video generation (CORE-25) (#13082)	2026-05-04 21:01:22 -07:00
Jedrzej Kosinski	e758594e3b	Add deploy environment header (Comfy-Env) to partner node API calls (#13425)	2026-05-04 20:17:56 -07:00
Jedrzej Kosinski	ae457da84b	feat: add generic --feature-flag CLI arg and --list-feature-flags registry (#13685)	2026-05-04 19:50:26 -07:00
rattus	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
rattus	1ac78180b3	make control-net load order deterministic (#13701) ... Make this deterministic so speeds dont change base of load order. Load them in reverse order so whatever the caller lists first is the top priority.	2026-05-04 12:58:06 -07:00
rattus	c47633f3be	prefetch: guard against no offload (#13703) ... cast_ will return no stream if there is no work to do. guard against this is the consume logic.	2026-05-04 12:56:05 -07:00
Silver	b138133ffa	Enable triton comfy kitchen via cli-arg (#12730)	2026-05-03 14:07:21 -04:00
Jukka Seppänen	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
rattus	783782d5d7	Implement block prefetch + Lora Async load + and adopt in LTX (Speedup!) (CORE-111) (#13618) ... * mm: Use Aimdo raw allocator for cast buffers pytorch manages allocation of growing buffers on streams poorly. Pyt has no windows support for the expandable segments allocator (which is the right tool for this job), while also segmenting the memory by stream such that it can be generally re-used. So kick the problem to aimdo which can just grow a virtual region thats freed per stream. * plan * ops: move cpu handler up to the caller * ops: split up prefetch from weight prep block prefetching API Split up the casting and weight formating/lora stuff in prep for arbitrary prefetch support. * ops: implement block prefetching API allow a model to construct a prefetch list and operate it for increased async offload. * ltxv2: Implement block prefetching * Implement lora async offload Implement async offload of loras.	2026-05-02 19:23:24 -04:00
Simon Lui	63103d519e	Remove IPEX and clean up checks and add missing synchronize during empty cache. (#13653)	2026-05-01 14:16:41 -07:00
Talmaj	cf9cbec596	Reformat models variable into multiline array CORE-59 (#13513) ... Co-authored-by: Talmaj Marinc <talmaj@comfy.org>	2026-05-01 17:20:11 +08:00
Rainer	e9c311b245	OneTainer ERNIE LoRA support (#13640)	2026-04-30 19:33:41 -04:00
blepping	a164c82913	Add high quality preview support for Flux2 latents (#13496)	2026-04-29 19:37:30 -04:00
Talmaj	5eeae3f1d8	Cogvideox (#13402) ... --------- Co-authored-by: kijai <40791699+kijai@users.noreply.github.com> Co-authored-by: Talmaj Marinc <talmaj@comfy.org>	2026-04-29 19:30:08 -04:00
Jukka Seppänen	0e25a6936e	Reduce video tiny VAE peak VRAM and decode time (CORE-127) (#13617) ... * Update taehv.py * Simplify * Simplify pixel_unshuffle dispatch	2026-04-29 12:15:10 -07:00
rattus	fce0398470	dynamicVRAM + --cache-ram 2 (CORE-117) (#13603) ... * pinned_memory: remove JIT RAM pressure release This doesn't work, as freeing intermediates for pins needs to be higher-priority than freeing pins-for-pins if and when you are going to do that. So this is too late as pins-for-pins is model load time and we dont have JIT pins-for-pins. * cacheing: Add a filter to only free intermediates from inactive wfs This is to get priorities in amongst pins straight. * mm: free inactive-ram from RAM cache first Stuff from inactive workflows should be freed before anything else. * caching: purge old ModelPatchers first Dont try and score them, just dump them at the first sign of trouble if they arent part of the workflow.	2026-04-28 19:15:02 -04:00
rattus	b47f15f25a	fix: Handle un-inited meta-tensors in models (fixes a CPU TE crash) (CORE-67) (#13578)	2026-04-27 22:22:31 -04:00