wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-12-16 17:42:58 +08:00
Code Issues Actions 13 Packages Projects Releases Wiki Activity
3,575 Commits 53 Branches 100 Tags 1.2 GiB
520eb77b72
Commit Graph

312 Commits

Author SHA1 Message Date
comfyanonymous
0075c6d096 Mixed precision diffusion models with scaled fp8. 
This change allows supports for diffusion models where all the linears are
scaled fp8 while the other weights are the original precision.
 2024-10-21 18:12:51 -04:00
comfyanonymous
83ca891118 Support scaled fp8 t5xxl model. 2024-10-20 22:27:00 -04:00
comfyanonymous
a68bbafddb Support diffusion models with scaled fp8 weights. 2024-10-19 23:47:42 -04:00
comfyanonymous
6632365e16 model_options consistency between functions. 
weight_dtype -> dtype
 2024-10-11 20:51:19 -04:00
comfyanonymous
1b80895285 Make clip loader nodes support loading sd3 t5xxl in lower precision. 
Add attention mask support in the SD3 text encoder code.
 2024-10-10 15:06:15 -04:00
Dr.Lt.Data
5f9d5a244b
Hotfix for the div zero occurrence when memory_used_encode is 0 (#5121) 
https://github.com/comfyanonymous/ComfyUI/issues/5069#issuecomment-2382656368
 2024-10-09 23:34:34 -04:00
comfyanonymous
e38c94228b Add a weight_dtype fp8_e4m3fn_fast to the Diffusion Model Loader node. 
This is used to load weights in fp8 and use fp8 matrix multiplication.
 2024-10-09 19:43:17 -04:00
comfyanonymous
7d2467e830 Some minor cleanups. 2024-10-05 13:22:39 -04:00
comfyanonymous
abcd006b8c Allow more permutations of clip/t5 in dual clip loader. 2024-10-03 09:26:11 -04:00
comfyanonymous
d985d1d7dc CLIP Loader node now supports clip_l and clip_g only for SD3. 2024-10-02 04:25:17 -04:00
comfyanonymous
d1cdf51e1b Refactor some of the TE detection code. 2024-10-01 07:08:41 -04:00
comfyanonymous
ad66f7c7d8 Add model_options to load_controlnet function. 2024-09-19 08:23:35 -04:00
comfyanonymous
d514bb38ee 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
e813abbb2c Long CLIP L support for SDXL, SD3 and Flux. 
Use the *CLIPLoader nodes.
 2024-09-15 07:59:38 -04:00
comfyanonymous
d1a6bd6845 Support loading long clipl model with the CLIP loader node. 2024-08-20 10:46:36 -04:00
comfyanonymous
9eee470244 New load_text_encoder_state_dicts function. 
Now you can load text encoders straight from a list of state dicts.
 2024-08-19 17:36:35 -04:00
comfyanonymous
4f7a3cb6fb unet -> diffusion_models. 2024-08-17 21:31:04 -04:00
comfyanonymous
fca42836f2 Add model_options for text encoder. 2024-08-17 11:17:20 -04:00
comfyanonymous
74e124f4d7 Fix some issues with TE being in lowvram mode. 2024-08-12 23:42:21 -04:00
comfyanonymous
a562c17e8a load_unet -> load_diffusion_model with a model_options argument. 2024-08-12 23:20:57 -04:00
comfyanonymous
ad76574cb8 Fix some potential issues with the previous commits. 2024-08-12 00:23:29 -04:00
comfyanonymous
9acfe4df41 Support loading directly to vram with CLIPLoader node. 2024-08-12 00:06:01 -04:00
comfyanonymous
9829b013ea Fix mistake in last commit. 2024-08-12 00:00:17 -04:00
comfyanonymous
5c69cde037 Load TE model straight to vram if certain conditions are met. 2024-08-11 23:52:43 -04:00
comfyanonymous
e9589d6d92 Add a way to set model dtype and ops from load_checkpoint_guess_config. 2024-08-11 08:50:34 -04:00
comfyanonymous
0d82a798a5 Remove the ckpt_path from load_state_dict_guess_config. 2024-08-11 08:37:35 -04:00
ljleb
925fff26fd
alternative to load_checkpoint_guess_config that accepts a loaded state dict (#4249) 
* make alternative fn

* add back ckpt path as 2nd argument?
 2024-08-11 08:36:52 -04:00
comfyanonymous
b334605a66 Fix OOMs happening in some cases. 
A cloned model patcher sometimes reported a model was loaded on a device
when it wasn't.
 2024-08-06 13:36:04 -04:00
comfyanonymous
2ba5cc8b86 Fix some issues. 2024-08-03 15:06:40 -04:00
comfyanonymous
ba9095e5bd Automatically use fp8 for diffusion model weights if: 
Checkpoint contains weights in fp8.

There isn't enough memory to load the diffusion model in GPU vram.
 2024-08-03 13:45:19 -04:00
comfyanonymous
d7430a1651 Add a way to load the diffusion model in fp8 with UNETLoader node. 2024-08-01 13:30:51 -04:00
comfyanonymous
5f98de7697 Load flux t5 in fp8 if weights are in fp8. 2024-08-01 11:05:56 -04:00
comfyanonymous
1589b58d3e Basic Flux Schnell and Flux Dev model implementation. 2024-08-01 09:49:29 -04:00
comfyanonymous
4ba7fa0244 Refactor: Move sd2_clip.py to text_encoders folder. 2024-07-28 01:19:20 -04:00
comfyanonymous
a5f4292f9f
Basic hunyuan dit implementation. (#4102) 
* Let tokenizers return weights to be stored in the saved checkpoint.

* Basic hunyuan dit implementation.

* Fix some resolutions not working.

* Support hydit checkpoint save.

* Init with right dtype.

* Switch to optimized attention in pooler.

* Fix black images on hunyuan dit.
 2024-07-25 18:21:08 -04:00
comfyanonymous
f87810cd3e Let tokenizers return weights to be stored in the saved checkpoint. 2024-07-25 10:52:09 -04:00
comfyanonymous
10c919f4c7 Make it possible to load tokenizer data from checkpoints. 2024-07-24 16:43:53 -04:00
comfyanonymous
1305fb294c Refactor: Move some code to the comfy/text_encoders folder. 2024-07-15 17:36:24 -04:00
comfyanonymous
a3dffc447a Support AuraFlow Lora and loading model weights in diffusers format. 
You can load model weights in diffusers format using the UNETLoader node.
 2024-07-13 13:51:40 -04:00
comfyanonymous
9f291d75b3 AuraFlow model implementation. 2024-07-11 16:52:26 -04:00
comfyanonymous
f45157e3ac Fix error message never being shown. 2024-07-11 11:46:51 -04:00
comfyanonymous
5e1fced639 Cleaner support for loading different diffusion model types. 2024-07-11 11:37:31 -04:00
comfyanonymous
ffe0bb0a33 Remove useless code. 2024-07-10 20:33:12 -04:00
comfyanonymous
391c1046cf More flexibility with text encoder return values. 
Text encoders can now return other values to the CONDITIONING than the cond
and pooled output.
 2024-07-10 20:06:50 -04:00
comfyanonymous
4040491149 Better T5xxl detection. 2024-07-06 00:53:33 -04:00
comfyanonymous
d7484ef30c Support loading checkpoints with the UNETLoader node. 2024-07-03 11:34:32 -04:00
comfyanonymous
537f35c7bc Don't update dict if contiguous. 2024-07-02 20:21:51 -04:00
Alex "mcmonkey" Goodwin
3f46362d22
fix non-contiguous tensor saving (from channels-last) (#3932) 2024-07-02 20:16:33 -04:00
comfyanonymous
8ceb5a02a3 Support saving stable audio checkpoint that can be loaded back. 2024-06-27 11:06:52 -04:00
comfyanonymous
4ef1479dcd Multi dimension tiled scale function and tiled VAE audio encoding fallback. 2024-06-22 11:57:49 -04:00
comfyanonymous
1e2839f4d9 More proper tiled audio decoding. 2024-06-20 16:50:31 -04:00
comfyanonymous
0d6a57938e Support loading diffusers SD3 model format with UNETLoader node. 2024-06-19 22:21:18 -04:00
comfyanonymous
a45df69570 Basic tiled decoding for audio VAE. 2024-06-17 22:48:23 -04:00
comfyanonymous
6425252c4f Use fp16 as the default vae dtype for the audio VAE. 2024-06-16 13:12:54 -04:00
comfyanonymous
ca9d300a80 Better estimation for memory usage during audio VAE encoding/decoding. 2024-06-16 11:47:32 -04:00
comfyanonymous
746a0410d4 Fix VAEEncode with taesd3. 2024-06-16 03:10:04 -04:00
comfyanonymous
04e8798c37 Improvements to the TAESD3 implementation. 2024-06-16 02:04:24 -04:00
Dr.Lt.Data
df7db0e027
support TAESD3 (#3738) 2024-06-16 02:03:53 -04:00
comfyanonymous
bb1969cab7 Initial support for the stable audio open model. 2024-06-15 12:14:56 -04:00
comfyanonymous
69c8d6d8a6 Single and dual clip loader nodes support SD3. 
You can use the CLIPLoader to use the t5xxl only or the DualCLIPLoader to
use CLIP-L and CLIP-G only for sd3.
 2024-06-11 23:27:39 -04:00
comfyanonymous
0e49211a11 Load the SD3 T5xxl model in the same dtype stored in the checkpoint. 2024-06-11 17:03:26 -04:00
comfyanonymous
5889b7ca0a Support multiple text encoder configurations on SD3. 2024-06-11 13:14:43 -04:00
comfyanonymous
8c4a9befa7 SD3 Support. 2024-06-10 14:06:23 -04:00
comfyanonymous
0920e0e5fe Remove some unused imports. 2024-05-27 19:08:27 -04:00
comfyanonymous
e1489ad257 Fix issue with lowvram mode breaking model saving. 2024-05-11 21:55:20 -04:00
comfyanonymous
93e876a3be Remove warnings that confuse people. 2024-05-09 05:29:42 -04:00
comfyanonymous
c61eadf69a Make the load checkpoint with config function call the regular one. 
I was going to completely remove this function because it is unmaintainable
but I think this is the best compromise.

The clip skip and v_prediction parts of the configs should still work but
not the fp16 vs fp32.
 2024-05-06 20:04:39 -04:00
comfyanonymous
8dc19e40d1 Don't init a VAE model when there are no VAE weights. 2024-04-24 09:20:31 -04:00
comfyanonymous
c59fe9f254 Support VAE without quant_conv. 2024-04-18 21:05:33 -04:00
comfyanonymous
30abc324c2 Support properly saving CosXL checkpoints. 2024-04-08 00:36:22 -04:00
comfyanonymous
0ed72befe1 Change log levels. 
Logging level now defaults to info. --verbose sets it to debug.
 2024-03-11 13:54:56 -04:00
comfyanonymous
65397ce601 Replace prints with logging and add --verbose argument. 2024-03-10 12:14:23 -04:00
comfyanonymous
ca7c310a0e Support loading old CLIP models saved with CLIPSave. 2024-02-25 08:29:12 -05:00
comfyanonymous
c2cb8e889b Always return unprojected pooled output for gligen. 2024-02-25 07:33:13 -05:00
comfyanonymous
1cb3f6a83b Move text projection into the CLIP model code. 
Fix issue with not loading the SSD1B clip correctly.
 2024-02-25 01:41:08 -05:00
comfyanonymous
d91f45ef28 Some cleanups to how the text encoders are loaded. 2024-02-19 10:46:30 -05:00
comfyanonymous
3b2e579926 Support loading the Stable Cascade effnet and previewer as a VAE. 
The effnet can be used to encode images for img2img with Stage C.
 2024-02-19 04:10:01 -05:00
comfyanonymous
97d03ae04a StableCascade CLIP model support. 2024-02-16 13:29:04 -05:00
comfyanonymous
f83109f09b Stable Cascade Stage C. 2024-02-16 10:55:08 -05:00
comfyanonymous
5e06baf112 Stable Cascade Stage A. 2024-02-16 06:30:39 -05:00
comfyanonymous
38b7ac6e26 Don't init the CLIP model when the checkpoint has no CLIP weights. 2024-02-13 00:01:08 -05:00
comfyanonymous
da7a8df0d2 Put VAE key name in model config. 2024-01-30 02:24:38 -05:00
comfyanonymous
4871a36458 Cleanup some unused imports. 2024-01-21 21:51:22 -05:00
comfyanonymous
d76a04b6ea Add unfinished ImageOnlyCheckpointSave node to save a SVD checkpoint. 
This node is unfinished, SVD checkpoints saved with this node will
work with ComfyUI but not with anything else.
 2024-01-17 19:46:21 -05:00
comfyanonymous
a7874d1a8b Add support for the stable diffusion x4 upscaling model. 
This is an old model.

Load the checkpoint like a regular one and use the new
SD_4XUpscale_Conditioning node.
 2024-01-03 03:37:56 -05:00
comfyanonymous
5eddfdd80c Refactor VAE code. 
Replace constants with downscale_ratio and latent_channels.
 2024-01-02 13:24:34 -05:00
comfyanonymous
824e4935f5 Add dtype parameter to VAE object. 2023-12-12 12:03:29 -05:00
comfyanonymous
ba07cb748e Use faster manual cast for fp8 in unet. 2023-12-11 18:24:44 -05:00
comfyanonymous
9ac0b487ac Make --gpu-only put intermediate values in GPU memory instead of cpu. 2023-12-08 02:35:45 -05:00
comfyanonymous
983ebc5792 Use smart model management for VAE to decrease latency. 2023-11-28 04:58:51 -05:00
comfyanonymous
c45d1b9b67 Add a function to load a unet from a state dict. 2023-11-27 17:41:29 -05:00
comfyanonymous
871cc20e13 Support SVD img2vid model. 2023-11-23 19:41:33 -05:00
comfyanonymous
410bf07771 Make VAE memory estimation take dtype into account. 2023-11-22 18:17:19 -05:00
comfyanonymous
6a491ebe27 Allow model config to preprocess the vae state dict on load. 2023-11-21 16:29:18 -05:00
comfyanonymous
cd4fc77d5f Add taesd and taesdxl to VAELoader node. 
They will show up if both the taesd_encoder and taesd_decoder or taesdxl
model files are present in the models/vae_approx directory.
 2023-11-21 12:54:19 -05:00
comfyanonymous
0cf4e86939 Add some command line arguments to store text encoder weights in fp8. 
Pytorch supports two variants of fp8:
--fp8_e4m3fn-text-enc (the one that seems to give better results)
--fp8_e5m2-text-enc
 2023-11-17 02:56:59 -05:00
comfyanonymous
0a6fd49a3e Print leftover keys when using the UNETLoader. 2023-11-07 22:15:55 -05:00
comfyanonymous
2455aaed8a Allow model or clip to be None in load_lora_for_models. 2023-11-01 20:27:20 -04:00
comfyanonymous
2a134bfab9 Fix checkpoint loader with config. 2023-10-27 22:13:55 -04:00
comfyanonymous
6ec3f12c6e Support SSD1B model and make it easier to support asymmetric unets. 2023-10-27 14:45:15 -04:00