comfyanonymous c711b8f437 Add --fp16-intermediates to use fp16 for intermediate values between nodes (#12953) ... This is an experimental WIP option that might not work in your workflow but should lower memory usage if it does. Currently only the VAE and the load image node will output in fp16 when this option is turned on.		2026-03-14 19:18:19 -04:00
..
audio_encoders	Fix fp16 audio encoder models (#12811)	2026-03-06 18:20:07 -05:00
cldm
comfy_types	fix: use frontend-compatible format for Float gradient_stops (#12789)	2026-03-12 10:14:28 -07:00
extra_samplers
image_encoders
k_diffusion
ldm	Support flux 2 klein kv cache model: Use the FluxKVCache node. (#12905)	2026-03-12 11:30:50 -04:00
sd1_tokenizer
t2i_adapter
taesd
text_encoders	Support the LTXAV 2.3 model. (#12773)	2026-03-04 20:06:20 -05:00
weight_adapter
cli_args.py	Add --fp16-intermediates to use fp16 for intermediate values between nodes (#12953)	2026-03-14 19:18:19 -04:00
clip_config_bigg.json
clip_model.py
clip_vision_config_g.json
clip_vision_config_h.json
clip_vision_config_vitl_336_llava.json
clip_vision_config_vitl_336.json
clip_vision_config_vitl.json
clip_vision_siglip2_base_naflex.json
clip_vision_siglip_384.json
clip_vision_siglip_512.json
clip_vision.py
conds.py	Cleanups to the last PR. (#12646)	2026-02-26 01:30:31 -05:00
context_windows.py	fix: handle substep sigmas in context window set_step (#12719)	2026-03-01 09:38:30 -08:00
controlnet.py
diffusers_convert.py
diffusers_load.py
float.py	feat: Support mxfp8 (#12907)	2026-03-14 18:36:29 -04:00
gligen.py
hooks.py
latent_formats.py	Feat: z-image pixel space (model still training atm) (#12709)	2026-03-02 19:43:47 -05:00
lora_convert.py
lora.py	Fix text encoder lora loading for wrapped models (#12852)	2026-03-09 16:08:51 -04:00
memory_management.py	comfy aimdo 0.2.11 + Improved RAM Pressure release strategies - Windows speedups (#12925)	2026-03-13 22:18:08 -04:00
model_base.py	Support the LTXAV 2.3 model. (#12773)	2026-03-04 20:06:20 -05:00
model_detection.py	model_detection: deep clone pre edited edited weights (#12862)	2026-03-09 23:50:10 -04:00
model_management.py	Add --fp16-intermediates to use fp16 for intermediate values between nodes (#12953)	2026-03-14 19:18:19 -04:00
model_patcher.py	comfy aimdo 0.2.11 + Improved RAM Pressure release strategies - Windows speedups (#12925)	2026-03-13 22:18:08 -04:00
model_sampling.py
nested_tensor.py
ops.py	feat: Support mxfp8 (#12907)	2026-03-14 18:36:29 -04:00
options.py
patcher_extension.py
pinned_memory.py	comfy aimdo 0.2.11 + Improved RAM Pressure release strategies - Windows speedups (#12925)	2026-03-13 22:18:08 -04:00
pixel_space_convert.py
quant_ops.py	feat: Support mxfp8 (#12907)	2026-03-14 18:36:29 -04:00
rmsnorm.py
sample.py
sampler_helpers.py	Disable dynamic_vram when weight hooks applied (#12653)	2026-02-28 16:50:18 -05:00
samplers.py	Disable dynamic_vram when weight hooks applied (#12653)	2026-02-28 16:50:18 -05:00
sd1_clip_config.json
sd1_clip.py
sd.py	Add --fp16-intermediates to use fp16 for intermediate values between nodes (#12953)	2026-03-14 19:18:19 -04:00
sdxl_clip.py
supported_models_base.py
supported_models.py	Adjust memory usage factor of zeta model. (#12746)	2026-03-03 17:35:22 -05:00
utils.py	comfy aimdo 0.2.11 + Improved RAM Pressure release strategies - Windows speedups (#12925)	2026-03-13 22:18:08 -04:00
windows.py