comfyanonymous
a05692d331
Fix flux TE not loading t5 embeddings.
2024-09-24 22:57:22 -04:00
chaObserv
b3ca8146a0
Add dpmpp_2m_cfg_pp ( #4992 )
2024-09-24 02:42:56 -04:00
comfyanonymous
c02bf69b07
Make --listen listen on both ipv4 and ipv6 at the same time by default.
2024-09-23 04:38:19 -04:00
comfyanonymous
8f990c3fa4
Remove useless line.
2024-09-23 02:32:29 -04:00
comfyanonymous
fc89499f3e
Add an optional VAE input to the ControlNetApplyAdvanced node.
...
Deprecate the other controlnet nodes.
2024-09-22 01:24:52 -04:00
comfyanonymous
5c7e72f3b1
Load controlnet in fp8 if weights are in fp8.
2024-09-21 04:50:12 -04:00
comfyanonymous
79a85a5253
Add load_controlnet_state_dict function.
2024-09-21 01:51:51 -04:00
comfyanonymous
bb9c7d4bbd
Add an error message when a controlnet needs a VAE but none is given.
2024-09-21 01:33:18 -04:00
comfyanonymous
25ecfd9295
Fix model merging issue.
2024-09-20 02:31:44 -04:00
yoinked
65b99536ee
add laplace scheduler [2407.03297] ( #4990 )
...
* add laplace scheduler [2407.03297]
* should be here instead lol
* better settings
2024-09-19 23:23:09 -04:00
comfyanonymous
6b6c490b4c
Add model_options to load_controlnet function.
2024-09-19 08:23:35 -04:00
Simon Lui
c4affc7e35
Fix xpu Pytorch nightly build from calling optimize which doesn't exist. ( #4978 )
2024-09-19 05:11:42 -04:00
pharmapsychotic
2f9f603a4f
Improve tiling calculations to reduce number of tiles that need to be processed. ( #4944 )
2024-09-17 03:51:10 -04:00
comfyanonymous
835d306666
Add some option to model_options for the text encoder.
...
load_device, offload_device and the initial_device can now be set.
2024-09-17 03:49:54 -04:00
comfyanonymous
29c18d1e69
get_key_patches now works without unloading the model.
2024-09-17 01:57:59 -04:00
comfyanonymous
28b12fb344
Long CLIP L support for SDXL, SD3 and Flux.
...
Use the *CLIPLoader nodes.
2024-09-15 07:59:38 -04:00
comfyanonymous
8058b19f35
Support AliMama SD3 and Flux inpaint controlnets.
...
Use the ControlNetInpaintingAliMamaApply node.
2024-09-14 09:05:16 -04:00
comfyanonymous
facf29d4f6
Support loading controlnets with different input.
2024-09-13 09:54:37 -04:00
Robin Huang
2db65988c5
Add cli arg to override user directory ( #4856 )
...
* Override user directory.
* Use overridden user directory.
* Remove prints.
* Remove references to global user_files.
* Remove unused replace_folder function.
* Remove newline.
* Remove global during get_user_directory.
* Add validation.
2024-09-12 08:10:27 -04:00
comfyanonymous
16568f960c
types -> comfy_types to fix import issue.
2024-09-12 03:57:46 -04:00
comfyanonymous
2e36788c9c
Doesn't really make sense for cfg_pp sampler to call regular one.
2024-09-11 02:51:36 -04:00
yoinked
f482299948
Add CFG++ to DPM++ 2S Ancestral ( #3871 )
...
* Update sampling.py
* Update samplers.py
* my bad
* "fix" the sampler
* Update samplers.py
* i named it wrong
* minor sampling improvements
mainly using a dynamic rho value (hey this sounds a lot like smea!!!)
* revert rho change
rho? r? its just 1/2
2024-09-11 02:49:44 -04:00
comfyanonymous
8690bb10f0
Fix lora issue.
2024-09-08 10:10:47 -04:00
comfyanonymous
035e8c218c
Support onetrainer text encoder Flux lora.
2024-09-08 09:31:41 -04:00
Jim Winkens
70acab9713
Fix import issue ( #4815 )
2024-09-07 05:28:32 -04:00
comfyanonymous
f45e0da17d
Support a generic Comfy format for text encoder loras.
...
This is a format with keys like:
text_encoders.clip_l.transformer.text_model.encoder.layers.9.self_attn.v_proj.lora_up.weight
Instead of waiting for me to add support for specific lora formats you can
convert your text encoder loras to this format instead.
If you want to see an example save a text encoder lora with the SaveLora
node with the commit right after this one.
2024-09-07 02:20:39 -04:00
comfyanonymous
46fb0fe3f5
Fix onnx export not working on flux.
2024-09-06 03:21:52 -04:00
comfyanonymous
f55860e83b
Mistoline flux controlnet support.
2024-09-05 00:05:17 -04:00
comfyanonymous
ebba1f2563
Prioritize freeing partially offloaded models first.
2024-09-04 19:47:32 -04:00
Jedrzej Kosinski
87ab41d767
Add emb_patch support to UNetModel forward ( #4779 )
2024-09-04 14:35:15 -04:00
Silver
0f7e7191a1
Make live preview size a configurable launch argument ( #4649 )
...
* Make live preview size a configurable launch argument
* Remove import from testing phase
* Update cli_args.py
2024-09-03 19:16:38 -04:00
comfyanonymous
e86a521904
Support newer glora format.
2024-09-03 17:02:19 -04:00
comfyanonymous
19c503d13f
Lower fp8 lora memory usage.
2024-09-03 01:25:05 -04:00
comfyanonymous
8fe38e1bbf
Flux onetrainer lora.
2024-09-02 08:22:15 -04:00
comfyanonymous
ac3c801c9d
Speed up inference on nvidia 10 series on Linux.
2024-09-01 17:29:31 -04:00
comfyanonymous
8e7d3547e4
Make minimum_inference_memory() depend on --reserve-vram
2024-09-01 01:18:34 -04:00
comfyanonymous
19cdff6796
Cleanup.
2024-08-30 12:53:59 -04:00
Chenlei Hu
2ff5eb9c72
Get logs endpoint & system_stats additions ( #4690 )
...
* Add route for getting output logs
* Include ComfyUI version
* Move to own function
* Changed to memory logger
* Unify logger setup logic
* Fix get version git fallback
---------
Co-authored-by: pythongosssss <125205205+pythongosssss@users.noreply.github.com>
2024-08-30 12:46:37 -04:00
comfyanonymous
573d09ea33
Fix potential issue with hydit controlnets.
2024-08-30 04:58:41 -04:00
comfyanonymous
ece9de35de
Fix glora lowvram issue.
2024-08-29 19:07:23 -04:00
comfyanonymous
c3503e62bc
Implement model part of flux union controlnet.
2024-08-29 18:41:22 -04:00
comfyanonymous
ee3374957b
InstantX depth flux controlnet.
2024-08-29 02:14:19 -04:00
comfyanonymous
739d31c73a
InstantX canny controlnet.
2024-08-28 19:02:50 -04:00
comfyanonymous
48a1a6ef98
Unify RMSNorm code.
2024-08-28 16:56:38 -04:00
comfyanonymous
a80296ecb6
Fix case where model was not properly unloaded in merging workflows.
2024-08-27 19:03:51 -04:00
Chenlei Hu
2f6fe893b3
Support weight padding on diff weight patch ( #4576 )
2024-08-27 13:55:37 -04:00
comfyanonymous
23922a2fbd
Do RMSNorm in native type.
2024-08-27 02:41:56 -04:00
comfyanonymous
f2a13e96b4
Make the stochastic fp8 rounding reproducible.
2024-08-26 15:12:06 -04:00
comfyanonymous
6c7971a4d7
Use less memory in float8 lora patching by doing calculations in fp16.
2024-08-26 14:45:58 -04:00
comfyanonymous
0144d62aa9
Fix potential memory leak.
2024-08-26 02:07:32 -04:00
