Jedrzej Kosinski
59891b0f96
Made encode_from_tokens_scheduled work when no hooks are set on patcher
2024-11-19 17:17:01 -06:00
Jedrzej Kosinski
9b2b1303b7
Removed a .to call on results of calculate_weight in patch_hook_weight_to_device that was screwing up the intermediate results for fp8 prior to being passed into stochastic_rounding call
2024-11-18 20:42:51 -06:00
Jedrzej Kosinski
9fe3db4c3a
For encode_from_tokens_scheduled, allow start_percent and end_percent in add_dict to limit which scheduled conds get encoded for optimization purposes
2024-11-18 12:25:17 -06:00
Jedrzej Kosinski
365170af95
Merge branch 'master' into patch_hooks_improved_memory
2024-11-18 08:43:19 -06:00
Jedrzej Kosinski
de6013ccc4
Increased MemoryCounter minimum memory to leave free by *2 until a better way to get inference memory estimate of currently loaded models exists
2024-11-18 08:08:00 -06:00
Jedrzej Kosinski
0850ae5c04
Remove unnecessary torch.no_grad calls for hook patches
2024-11-18 07:38:11 -06:00
Jedrzej Kosinski
e844695292
Fixed issue with setting weights from hooks instead of copying them, added additional memory_counter check when caching hook patches
2024-11-18 07:25:53 -06:00
comfyanonymous
9a0a5d32ee
Add a skip layer guidance node that can also skip single layers.
...
This one should work for skipping the single layers of models like Flux
and Auraflow.
If you want to see how these models work and how many double/single layers
they have see the "ModelMerge*" nodes for the specific model.
2024-11-18 02:20:43 -05:00
Jedrzej Kosinski
f465004a58
Fix cached_hook_patches not respecting target_device/memory_counter results
2024-11-17 12:52:40 -06:00
comfyanonymous
d9f90965c8
Support block replace patches in auraflow.
2024-11-17 08:19:59 -05:00
comfyanonymous
41886af138
Add transformer options blocks replace patch to mochi.
2024-11-16 20:48:14 -05:00
Chenlei Hu
22a1d7ce78
Fix 3.8 compatibility in user_manager.py ( #5645 )
2024-11-16 20:42:21 -05:00
Jedrzej Kosinski
a20be20ac7
Added apply_to_conds to Set CLIP Hooks, modified relevant code to allow text encoding to automatically apply hooks to output conds when apply_to_conds is set to True
2024-11-16 17:37:57 -06:00
Jedrzej Kosinski
e177149ae4
Made opt_hooks append by default instead of replace, renamed comfy.hooks set functions to be more accurate
2024-11-16 16:40:45 -06:00
Chenlei Hu
4ac401af2b
Update web content to release v1.3.44 ( #5620 )
...
* Update web content to release v1.3.44
* nit
2024-11-15 20:17:15 -05:00
comfyanonymous
5fb59c8475
Add a node to block merge auraflow models.
2024-11-15 12:47:55 -05:00
Jedrzej Kosinski
bcc6a22178
Made WrapperHook functional, added another wrapper/callback getter, added ON_DETACH callback to ModelPatcher
2024-11-14 08:06:02 -06:00
comfyanonymous
122c9ca1ce
Add advanced model merging node for mochi.
2024-11-14 07:51:20 -05:00
comfyanonymous
3b9a6cf2b1
Fix issue with 3d masks.
2024-11-13 07:18:30 -05:00
comfyanonymous
3748e7ef7a
Fix regression.
2024-11-13 04:24:48 -05:00
Jedrzej Kosinski
96b2080971
Merge branch 'master' into patch_hooks_improved_memory
2024-11-12 16:43:30 -06:00
Jedrzej Kosinski
1470719db6
Added clip scheduling support to all other native ComfyUI text encoding nodes (sdxl, flux, hunyuan, sd3)
2024-11-12 10:55:19 -06:00
Jedrzej Kosinski
5909b06b2e
Removed Register/Direct hook nodes since they were present only for testing, removed diff-related weight hook calculation as improved_memory removes unload_model_clones and using sample time registered hooks is less hacky
2024-11-12 09:05:19 -06:00
Jedrzej Kosinski
1766d903ad
Fixed existing weight hook_patches (pre-registered) not working properly for CLIP
2024-11-12 08:12:12 -06:00
comfyanonymous
8ebf2d8831
Add block replace transformer_options to flux.
2024-11-12 08:00:39 -05:00
Bratzmeister
a72d152b0c
fix --cuda-device arg for AMD/HIP devices ( #5586 )
...
* fix --cuda-device arg for AMD/HIP devices
CUDA_VISIBLE_DEVICES is ignored for HIP devices/backend. Instead it uses HIP_VISIBLE_DEVICES. Setting this environment variable has no side effect for CUDA/NVIDIA so it can safely be set in any case and vice versa.
* deleted accidental if
2024-11-12 06:53:36 -05:00
comfyanonymous
eb476e6ea9
Allow 1D masks for 1D latents.
2024-11-11 14:44:52 -05:00
Jedrzej Kosinski
9330745f27
Merge branch 'improved_memory' into patch_hooks_improved_memory
2024-11-11 11:26:36 -06:00
Jedrzej Kosinski
4195dfb032
Merge branch 'master' into patch_hooks_improved_memory
2024-11-11 11:26:27 -06:00
Jedrzej Kosinski
66b3386ee7
Updated different hook types to reflect actual progress of implementation, initial scaffolding for working WrapperHook functionality
2024-11-11 10:13:02 -06:00
Jedrzej Kosinski
b12cc83c5b
Modified callbacks and wrappers so that unregistered types can be used, allowing custom_nodes to have their own unique callbacks/wrappers if desired
2024-11-11 09:05:07 -06:00
Jedrzej Kosinski
638c4086a3
Fixed inconsistency of results when schedule_clip is set to False, small renaming/typo fixing, added initial support for ControlNet extra_hooks to work in tandem with normal cond hooks, initial work on calc_cond_batch merging all subdicts in returned transformer_options
2024-11-11 08:41:08 -06:00
Dr.Lt.Data
2d28b0b479
improve: add descriptions for clip loaders ( #5576 )
2024-11-11 05:37:23 -05:00
comfyanonymous
8b275ce5be
Support auto detecting some zsnr anime checkpoints.
2024-11-11 05:34:11 -05:00
comfyanonymous
2a18e98ccf
Refactor so that zsnr can be set in the sampling_settings.
2024-11-11 04:55:56 -05:00
comfyanonymous
8a5281006f
Fix some custom nodes.
2024-11-10 22:41:00 -05:00
comfyanonymous
bdeb1c171c
Fast previews for mochi.
2024-11-10 03:39:35 -05:00
comfyanonymous
9c1ed58ef2
proper fix for sag.
2024-11-10 00:10:45 -05:00
comfyanonymous
8b90e50979
Properly handle and reshape masks when used on 3d latents.
2024-11-09 15:30:19 -05:00
pythongosssss
6ee066a14f
Live terminal output ( #5396 )
...
* Add /logs/raw and /logs/subscribe for getting logs on frontend
Hijacks stderr/stdout to send all output data to the client on flush
* Use existing send sync method
* Fix get_logs should return string
* Fix bug
* pass no server
* fix tests
* Fix output flush on linux
2024-11-08 19:13:34 -05:00
DenOfEquity
dd5b57e3d7
fix for SAG with Kohya HRFix/ Deep Shrink ( #5546 )
...
now works with arbitrary downscale factors
2024-11-08 18:16:29 -05:00
comfyanonymous
75a818c720
Move mochi latent node to: latent/video.
2024-11-08 08:33:44 -05:00
comfyanonymous
2865f913f7
Free memory before doing tiled decode.
2024-11-07 04:01:24 -05:00
comfyanonymous
b49616f951
Make VAEDecodeTiled node work with video VAEs.
2024-11-07 03:47:12 -05:00
comfyanonymous
5e29e7a488
Remove scaled_fp8 key after reading it to silence warning.
2024-11-06 04:56:42 -05:00
comfyanonymous
8afb97cd3f
Fix unknown VAE being detected as the mochi VAE.
2024-11-05 03:43:27 -05:00
contentis
69694f40b3
fix dynamic shape export ( #5490 )
2024-11-04 14:59:28 -05:00
Chenlei Hu
c49025f01b
Allow POST /userdata/{file} endpoint to return full file info ( #5446 )
...
* Refactor listuserdata
* Full info param
* Add tests
* Fix mock
* Add full_info support for move user file
2024-11-04 13:57:21 -05:00
Jedrzej Kosinski
9dde713347
Refactored hooks in calc_cond_batch to be part of get_area_and_mult tuple, added extra_hooks to ControlBase to allow custom controlnets w/ hooks, small cleanup and renaming
2024-11-04 05:46:27 -06:00
comfyanonymous
95972bab86
Fix issue.
2024-11-04 05:07:07 -05:00
