Chargeuk ed945a1790 Dependency Aware Node Caching for low RAM/VRAM machines (#7509) ... * add dependency aware cache that removed a cached node as soon as all of its decendents have executed. This allows users with lower RAM to run workflows they would otherwise not be able to run. The downside is that every workflow will fully run each time even if no nodes have changed. * remove test code * tidy code		2025-04-11 06:55:51 -04:00
..
cldm	Replace print with logging (#6138)	2024-12-20 16:24:55 -05:00
comfy_types	Deprecate InputTypeOptions.defaultInput (#7551)	2025-04-10 06:57:06 -04:00
extra_samplers	Uni pc sampler now works with audio and video models.	2025-01-18 05:27:58 -05:00
image_encoders	Add support for giant dinov2 image encoder.	2025-03-17 05:53:54 -04:00
k_diffusion	Guard the edge cases of noise term in er_sde (#7265)	2025-03-16 06:02:25 -04:00
ldm	Add activations_shape info in UNet models (#7482)	2025-04-04 21:27:54 -04:00
sd1_tokenizer
t2i_adapter
taesd
text_encoders	Add an image_interleave option to the Hunyuan image to video encode node.	2025-03-07 19:56:26 -05:00
checkpoint_pickle.py
cli_args.py	Dependency Aware Node Caching for low RAM/VRAM machines (#7509)	2025-04-11 06:55:51 -04:00
clip_config_bigg.json
clip_model.py	Support llava clip vision model.	2025-03-06 00:24:43 -05:00
clip_vision_config_g.json
clip_vision_config_h.json
clip_vision_config_vitl_336_llava.json	Support llava clip vision model.	2025-03-06 00:24:43 -05:00
clip_vision_config_vitl_336.json
clip_vision_config_vitl.json
clip_vision_siglip_384.json
clip_vision_siglip_512.json	Support 512 siglip model.	2025-04-05 07:01:01 -04:00
clip_vision.py	Support 512 siglip model.	2025-04-05 07:01:01 -04:00
conds.py	Remove unused function lcm in conds.py (#6572)	2025-01-23 05:54:09 -05:00
controlnet.py	Use fp16 if checkpoint weights are fp16 and the model supports it.	2025-02-27 16:39:57 -05:00
diffusers_convert.py	Remove useless code.	2025-01-24 06:15:54 -05:00
diffusers_load.py
float.py
gligen.py
hooks.py	Hooks Part 2 - TransformerOptionsHook and AdditionalModelsHook (#6377)	2025-01-11 12:20:23 -05:00
latent_formats.py	Initial Hunyuan3Dv2 implementation.	2025-03-19 16:52:58 -04:00
lora_convert.py	Support the wan fun reward loras.	2025-04-07 05:01:47 -04:00
lora.py	Only use stable cascade lora format with cascade model.	2025-02-01 06:35:22 -05:00
model_base.py	Remove useless code.	2025-03-29 20:12:56 -04:00
model_detection.py	Native LotusD Implementation (#7125)	2025-03-21 14:04:15 -04:00
model_management.py	MLU memory optimization (#7470)	2025-04-02 19:24:04 -04:00
model_patcher.py	Call unpatch_hooks at the start of ModelPatcher.partially_unload (#7253)	2025-03-16 06:02:45 -04:00
model_sampling.py	Automatically set the right sampling type for lotus.	2025-03-21 14:19:37 -04:00
ops.py	No need for scale_input when fp8 matrix mult is disabled.	2025-03-07 04:49:20 -05:00
options.py
patcher_extension.py	Add prepare_sampling wrapper allowing custom nodes to more accurately report noise_shape (#7500)	2025-04-09 09:43:35 -04:00
sample.py	Auto reshape 2d to 3d latent for single image generation on video model.	2024-12-29 02:26:49 -05:00
sampler_helpers.py	Add prepare_sampling wrapper allowing custom nodes to more accurately report noise_shape (#7500)	2025-04-09 09:43:35 -04:00
samplers.py	Add er_sde sampler (#7187)	2025-03-12 02:42:37 -04:00
sd1_clip_config.json
sd1_clip.py	Fix some things breaking when embeddings fail to apply.	2025-03-06 13:31:55 -05:00
sd.py	Disable partial offloading of audio VAE.	2025-04-04 21:24:56 -04:00
sdxl_clip.py	Make it easier to set a custom template for hunyuan video.	2025-03-04 09:26:05 -05:00
supported_models_base.py
supported_models.py	Support the WAN 2.1 fun control models.	2025-03-26 19:54:54 -04:00
utils.py	Support LTXV 0.9.5.	2025-03-05 00:13:49 -05:00