rattus 9bc893c5bb sd: bump HY1.5 VAE estimate (#11107) ... Im able to push vram above estimate on partial unload. Bump the estimate. This is experimentally determined with a 720P and 480P datapoint calibrating for 24GB VRAM total.		2025-12-04 09:50:36 -08:00
..
audio_encoders
cldm	Add better error message for common error. (#10846)	2025-11-23 04:55:22 -05:00
comfy_types
extra_samplers
image_encoders
k_diffusion
ldm	Implement temporal rolling VAE (Major VRAM reductions in Hunyuan and Kandinsky) (#10995)	2025-12-02 22:49:29 -05:00
sd1_tokenizer
t2i_adapter
taesd	Support video tiny VAEs (#10884)	2025-11-28 19:40:19 -05:00
text_encoders	Implement the Ovis image model. (#11030)	2025-12-01 20:56:17 -05:00
weight_adapter	Fix loras not working on mixed fp8. (#10899)	2025-11-26 00:07:58 -05:00
checkpoint_pickle.py
cli_args.py	feat: Support ComfyUI-Manager for pip version (#7555)	2025-12-01 22:32:52 -05:00
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_siglip_384.json
clip_vision_siglip_512.json
clip_vision.py
conds.py
context_windows.py
controlnet.py
diffusers_convert.py
diffusers_load.py
float.py
gligen.py
hooks.py
latent_formats.py	Support video tiny VAEs (#10884)	2025-11-28 19:40:19 -05:00
lora_convert.py
lora.py	Add some missing z image lora layers. (#10980)	2025-11-28 23:55:00 -05:00
model_base.py	Fix Flux2 reference image mem estimation. (#10905)	2025-11-26 02:36:19 -05:00
model_detection.py	Implement the Ovis image model. (#11030)	2025-12-01 20:56:17 -05:00
model_management.py	mm: wrap the raw stream in context manager (#10958)	2025-11-28 16:38:12 -05:00
model_patcher.py	mp: use look-ahead actuals for stream offload VRAM calculation (#11096)	2025-12-03 23:28:44 -05:00
model_sampling.py
nested_tensor.py
ops.py	Prs/lora reservations (reduce massive Lora reservations especially on Flux2) (#11069)	2025-12-03 02:28:45 -05:00
options.py
patcher_extension.py
pixel_space_convert.py
quant_ops.py	fix QuantizedTensor.is_contiguous (#10956) (#10959)	2025-11-28 16:33:07 -05:00
rmsnorm.py
sample.py
sampler_helpers.py
samplers.py
sd1_clip_config.json
sd1_clip.py	Fix case where text encoders where running on the CPU instead of GPU. (#11095)	2025-12-03 23:15:15 -05:00
sd.py	sd: bump HY1.5 VAE estimate (#11107)	2025-12-04 09:50:36 -08:00
sdxl_clip.py
supported_models_base.py
supported_models.py	Hack to make zimage work in fp16. (#11057)	2025-12-02 17:11:58 -05:00
utils.py	Add some missing z image lora layers. (#10980)	2025-11-28 23:55:00 -05:00