1274 Commits

Author SHA1 Message Date
comfyanonymous
bdeb1c171c Fast previews for mochi. 2024-11-10 03:39:35 -05:00
comfyanonymous
8b90e50979 Properly handle and reshape masks when used on 3d latents. 2024-11-09 15:30:19 -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
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
Jedrzej Kosinski
0fbefb8428 Refactored code to store wrappers and callbacks in transformer_options, added apply_model and diffusion_model.forward wrappers 2024-11-03 06:22:48 -06:00
comfyanonymous
6c9dbde7de Fix mochi all in one checkpoint t5xxl key names. 2024-11-03 01:40:42 -05:00
Jedrzej Kosinski
51e8d5554c Moved WrappersMP/CallbacksMP/WrapperExecutor to patcher_extension.py 2024-11-02 22:21:16 -05:00
comfyanonymous
fabf449feb Mochi VAE encoder. 2024-11-01 17:33:09 -04:00
Jedrzej Kosinski
e3c3722ec2 Merge branch 'improved_memory' into patch_hooks_improved_memory 2024-11-01 06:02:46 -05:00
comfyanonymous
bd5d8f150f Prevent and detect some types of memory leaks. 2024-11-01 06:55:42 -04:00
Jedrzej Kosinski
89934a465a Merge branch 'improved_memory' into patch_hooks_improved_memory 2024-11-01 03:59:43 -05:00
Jedrzej Kosinski
45f16c2dad Merge branch 'improved_memory' into patch_hooks_improved_memory 2024-11-01 03:58:17 -05:00
comfyanonymous
975927cc79 Remove useless function. 2024-11-01 04:40:33 -04:00
comfyanonymous
1735d4fb01 Fix issue. 2024-11-01 04:25:27 -04:00
Jedrzej Kosinski
16735c98e0 Make encode_from_tokens_scheduled call cleaner, rollback change in model_patcher.py for hook_patches_backup dict 2024-11-01 02:01:45 -05:00
comfyanonymous
d8bd2a9baa Less fragile memory management. 2024-11-01 02:41:51 -04:00
Jedrzej Kosinski
489846905e Optimized CLIP hook scheduling to treat same strength as same keyframe 2024-10-31 19:28:16 -05:00
Jedrzej Kosinski
3bcbcce88d Merge branch 'master' into patch_hooks 2024-10-31 18:34:05 -05:00
Aarni Koskela
1c8286a44b
Avoid SyntaxWarning in UniPC docstring (#5442) 2024-10-31 15:17:26 -04:00
comfyanonymous
1af4a47fd1 Bump up mac version for attention upcast bug workaround. 2024-10-31 15:15:31 -04:00
comfyanonymous
daa1565b93 Fix diffusers flux controlnet regression. 2024-10-30 13:11:34 -04:00
Jedrzej Kosinski
7a4d2fe523 Fix range check in get_hooks_for_clip_schedule so that proper keyframes get assigned to corresponding ranges 2024-10-30 05:37:30 -05:00
Jedrzej Kosinski
d5169df808 Added initial support within CLIP Text Encode (Prompt) node for scheduling weight hook CLIP strength via clip_start_percent/clip_end_percent on conds, added schedule_clip toggle to Set CLIP Hooks node, small cleanup/fixes 2024-10-30 04:56:09 -05:00
comfyanonymous
09fdb2b269 Support SD3.5 medium diffusers format weights and loras. 2024-10-30 04:24:00 -04:00
comfyanonymous
30c0c81351 Add a way to patch blocks in SD3. 2024-10-29 00:48:32 -04:00
comfyanonymous
13b0ff8a6f Update SD3 code. 2024-10-28 21:58:52 -04:00
comfyanonymous
c320801187 Remove useless line. 2024-10-28 17:41:12 -04:00
comfyanonymous
669d9e4c67 Set default shift on mochi to 6.0 2024-10-27 22:21:04 -04:00
comfyanonymous
9ee0a6553a float16 inference is a bit broken on mochi. 2024-10-27 04:56:40 -04:00
comfyanonymous
5cbb01bc2f Basic Genmo Mochi video model support.
To use:
"Load CLIP" node with t5xxl + type mochi
"Load Diffusion Model" node with the mochi dit file.
"Load VAE" with the mochi vae file.

EmptyMochiLatentVideo node for the latent.
euler + linear_quadratic in the KSampler node.
2024-10-26 06:54:00 -04:00
comfyanonymous
c3ffbae067 Make LatentUpscale nodes work on 3d latents. 2024-10-26 01:50:51 -04:00
Jedrzej Kosinski
2047bf211f Changed CreateHookModelAsLoraTest to be the new CreateHookModelAsLora, rename old ones as 'direct' and will be removed prior to merge 2024-10-25 19:58:38 -05:00
comfyanonymous
d605677b33 Make euler_ancestral work on flow models (credit: Ashen). 2024-10-25 19:53:44 -04:00
Jedrzej Kosinski
daeb2624a9 Fixed default conds not respecting hook keyframes, made keyframes not reset cache when strength is unchanged, fixed Cond Set Default Combine throwing error, fixed model-as-lora throwing error during calculate_weight after a recent ComfyUI update, small refactoring/scaffolding changes for hooks 2024-10-25 18:32:22 -05:00
PsychoLogicAu
af8cf79a2d
support SimpleTuner lycoris lora for SD3 (#5340) 2024-10-24 01:18:32 -04:00
Jedrzej Kosinski
4bbdf2bfe5 Merge branch 'master' into patch_hooks 2024-10-23 21:10:46 -05:00
comfyanonymous
66b0961a46 Fix ControlLora issue with last commit. 2024-10-23 17:02:40 -04:00
comfyanonymous
754597c8a9 Clean up some controlnet code.
Remove self.device which was useless.
2024-10-23 14:19:05 -04:00
comfyanonymous
915fdb5745 Fix lowvram edge case. 2024-10-22 16:34:50 -04:00
contentis
5a8a48931a
remove attention abstraction (#5324) 2024-10-22 14:02:38 -04:00
comfyanonymous
8ce2a1052c Optimizations to --fast and scaled fp8. 2024-10-22 02:12:28 -04:00
comfyanonymous
f82314fcfc Fix duplicate sigmas on beta scheduler. 2024-10-21 20:19:45 -04:00
comfyanonymous
0075c6d096 Mixed precision diffusion models with scaled fp8.
This change allows supports for diffusion models where all the linears are
scaled fp8 while the other weights are the original precision.
2024-10-21 18:12:51 -04:00
comfyanonymous
83ca891118 Support scaled fp8 t5xxl model. 2024-10-20 22:27:00 -04:00
comfyanonymous
f9f9faface Fixed model merging issue with scaled fp8. 2024-10-20 06:24:31 -04:00