comfyanonymous
b8ffb2937f
Memory tweaks.
2024-08-12 15:07:11 -04:00
comfyanonymous
5d43e75e5b
Fix some issues with the model sometimes not getting patched.
2024-08-12 12:27:54 -04:00
comfyanonymous
517f4a94e4
Fix some lora loading slowdowns.
2024-08-12 11:50:32 -04:00
comfyanonymous
52a471c5c7
Change name of log.
2024-08-12 10:35:06 -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
75b9b55b22
Fix issues with #4302 and support loading diffusers format flux.
2024-08-10 21:28:24 -04:00
Jaret Burkett
1765f1c60c
FLUX: Added full diffusers mapping for FLUX.1 schnell and dev. Adds full LoRA support from diffusers LoRAs. ( #4302 )
2024-08-10 21:26:41 -04:00
comfyanonymous
1de69fe4d5
Fix some issues with inference slowing down.
2024-08-10 16:21:25 -04:00
comfyanonymous
ae197f651b
Speed up hunyuan dit inference a bit.
2024-08-10 07:36:27 -04:00
comfyanonymous
1b5b8ca81a
Fix regression.
2024-08-09 21:45:21 -04:00
comfyanonymous
6678d5cf65
Fix regression.
2024-08-09 14:02:38 -04:00
TTPlanetPig
e172564eea
Update controlnet.py to fix the default controlnet weight as constant ( #4285 )
2024-08-09 13:40:05 -04:00
comfyanonymous
a3cc326748
Better fix for lowvram issue.
2024-08-09 12:16:25 -04:00
comfyanonymous
86a97e91fc
Fix controlnet regression.
2024-08-09 12:08:58 -04:00
comfyanonymous
5acdadc9f3
Fix issue with some lowvram weights.
2024-08-09 03:58:28 -04:00
comfyanonymous
55ad9d5f8c
Fix regression.
2024-08-09 03:36:40 -04:00
comfyanonymous
a9f04edc58
Implement text encoder part of HunyuanDiT loras.
2024-08-09 03:21:10 -04:00
comfyanonymous
a475ec2300
Cleanup HunyuanDit controlnets.
...
Use the: ControlNetApply SD3 and HunyuanDiT node.
2024-08-09 02:59:34 -04:00
来新璐
06eb9fb426
feat: add support for HunYuanDit ControlNet ( #4245 )
...
* add support for HunYuanDit ControlNet
* fix hunyuandit controlnet
* fix typo in hunyuandit controlnet
* fix typo in hunyuandit controlnet
* fix code format style
* add control_weight support for HunyuanDit Controlnet
* use control_weights in HunyuanDit Controlnet
* fix typo
2024-08-09 02:59:24 -04:00
comfyanonymous
413322645e
Raw torch is faster than einops?
2024-08-08 22:09:29 -04:00
comfyanonymous
11200de970
Cleaner code.
2024-08-08 20:07:09 -04:00
comfyanonymous
037c38eb0f
Try to improve inference speed on some machines.
2024-08-08 17:29:27 -04:00
comfyanonymous
1e11d2d1f5
Better prints.
2024-08-08 17:29:27 -04:00
comfyanonymous
66d4233210
Fix.
2024-08-08 15:16:51 -04:00
comfyanonymous
591010b7ef
Support diffusers text attention flux loras.
2024-08-08 14:45:52 -04:00
comfyanonymous
08f92d55e9
Partial model shift support.
2024-08-08 14:45:06 -04:00
comfyanonymous
8115d8cce9
Add Flux fp16 support hack.
2024-08-07 15:08:39 -04:00
comfyanonymous
6969fc9ba4
Make supported_dtypes a priority list.
2024-08-07 15:00:06 -04:00
comfyanonymous
cb7c4b4be3
Workaround for lora OOM on lowvram mode.
2024-08-07 14:30:54 -04:00
comfyanonymous
1208863eca
Fix "Comfy" lora keys.
...
They are in this format now:
diffusion_model.full.model.key.name.lora_up.weight
2024-08-07 13:49:31 -04:00
comfyanonymous
e1c528196e
Fix bundled embed.
2024-08-07 13:30:45 -04:00
comfyanonymous
17030fd4c0
Support for "Comfy" lora format.
...
The keys are just: model.full.model.key.name.lora_up.weight
It is supported by all comfyui supported models.
Now people can just convert loras to this format instead of having to ask
for me to implement them.
2024-08-07 13:18:32 -04:00
comfyanonymous
c19dcd362f
Controlnet code refactor.
2024-08-07 12:59:28 -04:00
comfyanonymous
1c08bf35b4
Support format for embeddings bundled in loras.
2024-08-07 03:45:25 -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
c14ac98fed
Unload models and load them back in lowvram mode no free vram.
2024-08-06 03:22:39 -04:00
comfyanonymous
2d75df45e6
Flux tweak memory usage.
2024-08-05 21:58:28 -04:00
comfyanonymous
8edbcf5209
Improve performance on some lowend GPUs.
2024-08-05 16:24:04 -04:00
a-One-Fan
a178e25912
Fix Flux FP64 math on XPU ( #4210 )
2024-08-05 01:26:20 -04:00
comfyanonymous
78e133d041
Support simple diffusers Flux loras.
2024-08-04 22:05:48 -04:00
Silver
7afa985fba
Correct spelling 'token_weight_pars_t5' to 'token_weight_pairs_t5' ( #4200 )
2024-08-04 17:10:02 -04:00
comfyanonymous
3b71f84b50
ONNX tracing fixes.
2024-08-04 15:45:43 -04:00
comfyanonymous
0a6b008117
Fix issue with some custom nodes.
2024-08-04 10:03:33 -04:00
comfyanonymous
f7a5107784
Fix crash.
2024-08-03 16:55:38 -04:00
comfyanonymous
91be9c2867
Tweak lowvram memory formula.
2024-08-03 16:44:50 -04:00
comfyanonymous
03c5018c98
Lower lowvram memory to 1/3 of free memory.
2024-08-03 15:14:07 -04:00
comfyanonymous
2ba5cc8b86
Fix some issues.
2024-08-03 15:06:40 -04:00
comfyanonymous
1e68002b87
Cap lowvram to half of free memory.
2024-08-03 14:50:20 -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
f123328b82
Load T5 in fp8 if it's in fp8 in the Flux checkpoint.
2024-08-03 12:39:33 -04:00
comfyanonymous
63a7e8edba
More aggressive batch splitting.
2024-08-03 11:53:30 -04:00
comfyanonymous
ea03c9dcd2
Better per model memory usage estimations.
2024-08-02 18:09:24 -04:00
comfyanonymous
3a9ee995cf
Tweak regular SD memory formula.
2024-08-02 17:34:30 -04:00
comfyanonymous
47da42d928
Better Flux vram estimation.
2024-08-02 17:02:35 -04:00
Alexander Brown
ce9ac2fe05
Fix clip_g/clip_l mixup ( #4168 )
2024-08-01 21:40:56 -04:00
comfyanonymous
e638f2858a
Hack to make all resolutions work on Flux models.
2024-08-01 21:39:18 -04:00
comfyanonymous
d420bc792a
Tweak the memory usage formulas for Flux and SD.
2024-08-01 17:53:45 -04:00
comfyanonymous
d965474aaa
Make ComfyUI split batches a higher priority than weight offload.
2024-08-01 16:39:59 -04:00
comfyanonymous
1c61361fd2
Fast preview support for Flux.
2024-08-01 16:28:11 -04:00
comfyanonymous
a6decf1e62
Fix bfloat16 potentially not being enabled on mps.
2024-08-01 16:18:44 -04:00
comfyanonymous
48eb1399c0
Try to fix mac issue.
2024-08-01 13:41:27 -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
f2b80f95d2
Better Mac support on flux model.
2024-08-01 13:10:50 -04:00
comfyanonymous
1aa9cf3292
Make lowvram more aggressive on low memory machines.
2024-08-01 12:11:57 -04:00
comfyanonymous
eb96c3bd82
Fix .sft file loading (they are safetensors files).
2024-08-01 11:32:58 -04:00
comfyanonymous
5f98de7697
Load flux t5 in fp8 if weights are in fp8.
2024-08-01 11:05:56 -04:00
comfyanonymous
8d34211a7a
Fix old python versions no longer working.
2024-08-01 09:57:20 -04:00
comfyanonymous
1589b58d3e
Basic Flux Schnell and Flux Dev model implementation.
2024-08-01 09:49:29 -04:00
comfyanonymous
7ad574bffd
Mac supports bf16 just make sure you are using the latest pytorch.
2024-08-01 09:42:17 -04:00
comfyanonymous
e2382b6adb
Make lowvram less aggressive when there are large amounts of free memory.
2024-08-01 03:58:58 -04:00
comfyanonymous
c24f897352
Fix to get fp8 working on T5 base.
2024-07-31 02:00:19 -04:00
comfyanonymous
a5991a7aa6
Fix hunyuan dit text encoder weights always being in fp32.
2024-07-31 01:34:57 -04:00
comfyanonymous
2c038ccef0
Lower CLIP memory usage by a bit.
2024-07-31 01:32:35 -04:00
comfyanonymous
b85216a3c0
Lower T5 memory usage by a few hundred MB.
2024-07-31 00:52:34 -04:00
comfyanonymous
82cae45d44
Fix potential issue with non clip text embeddings.
2024-07-30 14:41:13 -04:00
comfyanonymous
25853d0be8
Use common function for casting weights to input.
2024-07-30 10:49:14 -04:00
comfyanonymous
79040635da
Remove unnecessary code.
2024-07-30 05:01:34 -04:00
comfyanonymous
66d35c07ce
Improve artifacts on hydit, auraflow and SD3 on specific resolutions.
...
This breaks seeds for resolutions that are not a multiple of 16 in pixel
resolution by using circular padding instead of reflection padding but
should lower the amount of artifacts when doing img2img at those
resolutions.
2024-07-29 20:48:50 -04:00
comfyanonymous
4ba7fa0244
Refactor: Move sd2_clip.py to text_encoders folder.
2024-07-28 01:19:20 -04:00
comfyanonymous
cf4418b806
Don't treat Bert model like CLIP.
...
Bert can accept up to 512 tokens so any prompt with more than 77 should
just be passed to it as is instead of splitting it up like CLIP.
2024-07-26 13:08:12 -04:00
comfyanonymous
8328a2d8cd
Let hunyuan dit work with all prompt lengths.
2024-07-26 12:11:32 -04:00
comfyanonymous
afe732bef9
Hunyuan dit can now accept longer prompts.
2024-07-26 11:52:58 -04:00
comfyanonymous
a9ac56fc0d
Own BertModel implementation that works with lowvram.
2024-07-26 04:47:17 -04:00
comfyanonymous
25b51b1a8b
Hunyuan DiT lora support.
2024-07-25 22:42:54 -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
10b43ceea5
Remove duplicate code.
2024-07-24 01:12:59 -04:00
comfyanonymous
0a4c49c57c
Support MT5.
2024-07-23 15:35:28 -04:00
comfyanonymous
88ed893034
Allow SPieceTokenizer to load model from a byte string.
2024-07-23 14:17:42 -04:00
comfyanonymous
334ba48cea
More generic unet prefix detection code.
2024-07-23 14:13:32 -04:00
comfyanonymous
14764aa2e2
Rename LLAMATokenizer to SPieceTokenizer.
2024-07-22 12:21:45 -04:00
comfyanonymous
b2c995f623
"auto" type is only relevant to the SetUnionControlNetType node.
2024-07-22 11:30:38 -04:00
Chenlei Hu
4151fbfa8a
Add error message on union controlnet ( #4081 )
2024-07-22 11:27:32 -04:00
