2452 Commits

Author SHA1 Message Date
comfyanonymous
b0eaa09c6a Better per model memory usage estimations. 2024-08-02 18:09:24 -04:00
comfyanonymous
e2284e5609 Tweak regular SD memory formula. 2024-08-02 17:34:30 -04:00
comfyanonymous
ebc7233402 Better Flux vram estimation. 2024-08-02 17:02:35 -04:00
comfyanonymous
cd49c56d20 Fix bug loading flac workflow when it contains = character. 2024-08-02 13:14:28 -04:00
fgdfgfthgr-fox
fccdd04ee7 Lower SAG scale step for finer control (#4158)
* Lower SAG step for finer control

Since the introduction of cfg++ which uses very low cfg value, a step of 0.1 in SAG might be too high for finer control. Even SAG of 0.1 can be too high when cfg is only 0.6, so I change the step to 0.01.

* Lower PAG step as well.

* Update nodes_sag.py
2024-08-02 10:29:03 -04:00
comfyanonymous
851720f59f Add FluxGuidance node.
This lets you adjust the guidance on the dev model which is a parameter
that is passed to the diffusion model.
2024-08-02 10:25:49 -04:00
Jairo Correa
794358e877 Add missing import (#4174) 2024-08-02 09:34:12 -04:00
comfyanonymous
33912774fb Fix no longer working on old pytorch. 2024-08-01 22:20:24 -04:00
Alexander Brown
90267ffb3a Fix clip_g/clip_l mixup (#4168) 2024-08-01 21:40:56 -04:00
comfyanonymous
a06d0ff763 Hack to make all resolutions work on Flux models. 2024-08-01 21:39:18 -04:00
comfyanonymous
2c3ecacc4d Add CLIPTextEncodeFlux. 2024-08-01 18:53:25 -04:00
comfyanonymous
49c0c333d3 Tweak the memory usage formulas for Flux and SD. 2024-08-01 17:53:45 -04:00
comfyanonymous
f176649e08 Make ComfyUI split batches a higher priority than weight offload. 2024-08-01 16:39:59 -04:00
comfyanonymous
516d71d227 Fast preview support for Flux. 2024-08-01 16:28:11 -04:00
comfyanonymous
f5b2fc6e6b Fix bfloat16 potentially not being enabled on mps. 2024-08-01 16:18:44 -04:00
comfyanonymous
bd6f023ff6 Try to fix mac issue. 2024-08-01 13:41:27 -04:00
comfyanonymous
085eed028e Rename UNETLoader node to "Load Diffusion Model". 2024-08-01 13:33:30 -04:00
comfyanonymous
5606d85b07 Add a way to load the diffusion model in fp8 with UNETLoader node. 2024-08-01 13:30:51 -04:00
comfyanonymous
30a15dd5e1 Better Mac support on flux model. 2024-08-01 13:10:50 -04:00
comfyanonymous
faad5f1cdb Make lowvram more aggressive on low memory machines. 2024-08-01 12:11:57 -04:00
comfyanonymous
c0797230e2 Add link to Flux examples to readme. 2024-08-01 11:48:19 -04:00
comfyanonymous
5d5b9dcf89 Fix .sft file loading (they are safetensors files). 2024-08-01 11:32:58 -04:00
comfyanonymous
d6d48306d8 Load flux t5 in fp8 if weights are in fp8. 2024-08-01 11:05:56 -04:00
comfyanonymous
96dbbd23d8 Fix old python versions no longer working. 2024-08-01 09:57:20 -04:00
comfyanonymous
fc6a27f36c Basic Flux Schnell and Flux Dev model implementation. 2024-08-01 09:49:29 -04:00
comfyanonymous
339a710a7a Mac supports bf16 just make sure you are using the latest pytorch. 2024-08-01 09:42:17 -04:00
comfyanonymous
78c273b0ba Make lowvram less aggressive when there are large amounts of free memory. 2024-08-01 03:58:58 -04:00
comfyanonymous
a4b37c2939 Fix to get fp8 working on T5 base. 2024-07-31 02:00:19 -04:00
comfyanonymous
c5b754fbb6 Fix hunyuan dit text encoder weights always being in fp32. 2024-07-31 01:34:57 -04:00
comfyanonymous
4e9abfb0d5 Lower CLIP memory usage by a bit. 2024-07-31 01:32:35 -04:00
comfyanonymous
7f0000bc5a Lower T5 memory usage by a few hundred MB. 2024-07-31 00:52:34 -04:00
comfyanonymous
671fba8c0d Fix potential issue with non clip text embeddings. 2024-07-30 14:41:13 -04:00
comfyanonymous
36b0b2b215 Use common function for casting weights to input. 2024-07-30 10:49:14 -04:00
comfyanonymous
d0cc951625 Remove unnecessary code. 2024-07-30 05:01:34 -04:00
comfyanonymous
7f112b9d5d 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
66bdf820a1 Less confusing exception if pillow() function fails. 2024-07-29 11:15:37 -04:00
comfyanonymous
79ea2d3d12 Refactor: Move sd2_clip.py to text_encoders folder. 2024-07-28 01:19:20 -04:00
bymyself
dc40c5fa3b Active workflow use primary fg color (#4090) 2024-07-27 23:34:19 -04:00
Silver
c82c3556f7 Add dpmpp_2s_ancestral as custom sampler (#4101)
Adding dpmpp_2s_ancestral as custom sampler node to enable its use with eta and s_noise when using custom sampling.
2024-07-27 16:19:50 -04:00
comfyanonymous
9898e8845e Update packaging workflow. 2024-07-27 04:48:19 -04:00
comfyanonymous
50852646a6 Add a way to set custom dependencies in the release workflow. 2024-07-27 04:41:46 -04:00
comfyanonymous
611e0d2a67 Handle case in the updater when master branch is not in local repo. 2024-07-27 03:15:22 -04:00
comfyanonymous
66af046ab9 Update nightly package workflow. 2024-07-27 01:20:18 -04:00
comfyanonymous
9a9820777c Set stable releases as a prerelease initially.
This should give time to test the standalone package before making it live.
2024-07-26 14:52:20 -04:00
Robin Huang
39de3a64f4 Change windows standalone URL to stable release. (#4065) 2024-07-26 14:37:40 -04:00
comfyanonymous
f4a8f8db50 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
5b87251031 Add CLIPTextEncodeHunyuanDiT.
Useful for testing what each text encoder does.
2024-07-26 13:08:06 -04:00
filtered
350ddb0cc1 Fix undo incorrectly undoing text input (#4114)
Fixes an issue where under certain conditions, the ComfyUI custom undo / redo functions would not run when intended to.

When trying to undo an action like deleting several nodes, instead the native browser undo runs - e.g. a textarea gets focus and the last typed text is undone.  Clicking outside the text area and typing again just keeps doing the same thing.
2024-07-26 12:25:42 -04:00
comfyanonymous
a787d2dfc0 Let hunyuan dit work with all prompt lengths. 2024-07-26 12:11:32 -04:00
comfyanonymous
1824ded587 Hunyuan dit can now accept longer prompts. 2024-07-26 11:52:58 -04:00