Commit Graph

109 Commits

Author SHA1 Message Date
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
Jedrzej Kosinski 51e8d5554c Moved WrappersMP/CallbacksMP/WrapperExecutor to patcher_extension.py 2024-11-02 22:21:16 -05:00
Jedrzej Kosinski 45f16c2dad Merge branch 'improved_memory' into patch_hooks_improved_memory 2024-11-01 03:58:17 -05:00
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 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
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
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
Jedrzej Kosinski 4bbdf2bfe5 Merge branch 'master' into patch_hooks 2024-10-23 21:10:46 -05:00
comfyanonymous f9f9faface Fixed model merging issue with scaled fp8. 2024-10-20 06:24:31 -04:00
comfyanonymous a68bbafddb Support diffusion models with scaled fp8 weights. 2024-10-19 23:47:42 -04:00
Jedrzej Kosinski 1f8d9c040b Fixed models not being unloaded properly due to current_patcher reference; the current ComfyUI model cleanup code requires that nothing else has a reference to the ModelPatcher instances 2024-10-11 06:50:55 -05:00
Jedrzej Kosinski 06fbdb03ef Merge branch 'master' into patch_hooks 2024-10-05 06:43:43 -05:00
comfyanonymous 3bb4dec720 Fix issue with loras, lowvram and --fast fp8. 2024-09-28 14:42:32 -04:00
kosinkadink1@gmail.com 0f7d379d24 Refactored WrapperExecutor code to remove need for WrapperClassExecutor (now gone), added sampler.sample wrapper (pending review, will likely keep but will see what hacks this could currently let me get rid of in ACN/ADE) 2024-09-27 12:14:36 +09:00
kosinkadink1@gmail.com 09cbd69161 Added create_model_options_clone func, modified type annotations to use __future__ so that I can use the better type annotations 2024-09-25 20:29:49 +09:00
kosinkadink1@gmail.com d3229cbba7 Implement basic MemoryCounter system for determing with cached weights due to hooks should be offloaded in hooks_backup 2024-09-24 17:28:18 +09:00
kosinkadink1@gmail.com c422553b0b Added get_attachment func on ModelPatcher 2024-09-24 16:20:53 +09:00
kosinkadink1@gmail.com da6c0455cc Added forward_timestep_embed_patch type, added helper functions on ModelPatcher for emb_patch and forward_timestep_embed_patch, added helper functions for removing callbacks/wrappers/additional_models by key, added custom_should_register prop to hooks 2024-09-24 12:40:54 +09:00
kosinkadink1@gmail.com 7c86407619 Refactored callbacks+wrappers to allow storing lists by id 2024-09-22 16:36:40 +09:00
kosinkadink1@gmail.com 5052a78be2 Added WrapperExecutor for non-classbound functions, added calc_cond_batch wrappers 2024-09-22 11:52:35 +09:00
kosinkadink1@gmail.com 298397d198 Updated clone_has_same_weights function to account for new ModelPatcher properties, improved AutoPatcherEjector usage in partially_load 2024-09-21 21:50:51 +09:00
kosinkadink1@gmail.com f28d892c16 Fix skip_until_exit logic bug breaking injection after first run of model 2024-09-21 16:34:40 +09:00
kosinkadink1@gmail.com 5f450d3351 Started scaffolding for other hook types, refactored get_hooks_from_cond to organize hooks by type 2024-09-21 10:37:18 +09:00
kosinkadink1@gmail.com 59d72b4050 Added wrappers to ModelPatcher to facilitate standardized function wrapping 2024-09-20 20:05:29 +09:00
kosinkadink1@gmail.com 55014293b1 Added injections support to ModelPatcher + necessary bookkeeping, added additional_models support in ModelPatcher, conds, and hooks 2024-09-19 21:43:58 +09:00
kosinkadink1@gmail.com e80dc96627 Fix incorrect ref to create_hook_patches_clone after moving function 2024-09-19 11:57:19 +09:00
kosinkadink1@gmail.com 787ef34842 Continued work on simpler Create Hook Model As LoRA node, started to implement ModelPatcher callbacks, attachments, and additional_models 2024-09-19 11:47:25 +09:00
kosinkadink1@gmail.com 6b14fc8795 Merge branch 'master' into patch_hooks 2024-09-17 15:31:03 +09:00
comfyanonymous 0849c80e2a get_key_patches now works without unloading the model. 2024-09-17 01:57:59 -04:00
kosinkadink1@gmail.com 4b472ba44c Added support for adding weight hooks that aren't registered on the ModelPatcher at sampling time 2024-09-17 06:22:41 +09:00
kosinkadink1@gmail.com f5c899f42a Fixed MaxSpeed and default conds implementations 2024-09-15 21:00:45 +09:00
kosinkadink1@gmail.com a5034df6db Made CLIP work with hook patches 2024-09-15 15:47:09 +09:00
kosinkadink1@gmail.com 9ded65a616 Added initial set of hook-related nodes, added code to register hooks for loras/model-as-loras, small renaming/refactoring 2024-09-15 08:33:17 +09:00
kosinkadink1@gmail.com 5dadd97583 Added default_conds support in calc_cond_batch func 2024-09-14 17:21:50 +09:00
kosinkadink1@gmail.com f160d46340 Added call to initialize_timesteps on hooks in process_conds func, and added call prepare current keyframe on hooks in calc_cond_batch 2024-09-14 16:10:42 +09:00
kosinkadink1@gmail.com 1268d04295 Consolidated add_hook_patches_as_diffs into add_hook_patches func, fixed fp8 support for model-as-lora feature 2024-09-14 14:09:43 +09:00
kosinkadink1@gmail.com 069ec7a64b Added hook_patches to ModelPatcher for weights (model) 2024-09-13 17:20:22 +09:00
comfyanonymous 9d720187f1 types -> comfy_types to fix import issue. 2024-09-12 03:57:46 -04:00
comfyanonymous 2ca8f6e23d Make the stochastic fp8 rounding reproducible. 2024-08-26 15:12:06 -04:00
comfyanonymous c6812947e9 Fix potential memory leak. 2024-08-26 02:07:32 -04:00
comfyanonymous 7df42b9a23 Fix dora. 2024-08-23 04:58:59 -04:00
comfyanonymous c26ca27207 Move calculate function to comfy.lora 2024-08-22 17:12:00 -04:00
comfyanonymous 7c6bb84016 Code cleanups. 2024-08-22 17:05:12 -04:00
comfyanonymous 4d341b78e8 Bug fixes. 2024-08-19 16:28:55 -04:00
comfyanonymous 6138f92084 Use better dtype for the lowvram lora system. 2024-08-19 15:35:25 -04:00
comfyanonymous be0726c1ed Remove duplication. 2024-08-19 15:26:50 -04:00
comfyanonymous 20ace7c853 Code cleanup. 2024-08-19 12:48:59 -04:00
comfyanonymous bb222ceddb Fix loras having a weak effect when applied on fp8. 2024-08-17 15:20:17 -04:00
comfyanonymous cd5017c1c9 calculate_weight function to use a different dtype. 2024-08-17 01:06:08 -04:00