wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-01-21 20:00:17 +08:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity
1,594 Commits 64 Branches 111 Tags 1.3 GiB
e8b60dfc6e
Commit Graph

524 Commits

Author SHA1 Message Date
comfyanonymous
fe4c07400c Fix "Load Checkpoint with config" node. 2023-08-29 23:58:32 -04:00
comfyanonymous
f2f5e5dcbb Support SDXL t2i adapters with 3 channel input. 2023-08-29 16:44:57 -04:00
doctorpangloss
db673f7728 merge upstream 2023-08-29 13:36:53 -07:00
comfyanonymous
15adc3699f Move beta_schedule to model_config and allow disabling unet creation. 2023-08-29 14:22:53 -04:00
comfyanonymous
bed116a1f9 Remove optimization that caused border. 2023-08-29 11:21:36 -04:00
comfyanonymous
65cae62c71 No need to check filename extensions to detect shuffle controlnet. 2023-08-28 16:49:06 -04:00
comfyanonymous
4e89b2c25a Put clip vision outputs on the CPU. 2023-08-28 16:26:11 -04:00
comfyanonymous
a094b45c93 Load clipvision model to GPU for faster performance. 2023-08-28 15:29:27 -04:00
comfyanonymous
1300a1bb4c Text encoder should initially load on the offload_device not the regular. 2023-08-28 15:08:45 -04:00
comfyanonymous
f92074b84f Move ModelPatcher to model_patcher.py 2023-08-28 14:51:31 -04:00
comfyanonymous
4798cf5a62 Implement loras with norm keys. 2023-08-28 11:20:06 -04:00
comfyanonymous
b8c7c770d3 Enable bf16-vae by default on ampere and up. 2023-08-27 23:06:19 -04:00
comfyanonymous
1c794a2161 Fallback to slice attention if xformers doesn't support the operation. 2023-08-27 22:24:42 -04:00
comfyanonymous
d935ba50c4 Make --bf16-vae work on torch 2.0 2023-08-27 21:33:53 -04:00
comfyanonymous
a57b0c797b Fix lowvram model merging. 2023-08-26 11:52:07 -04:00
comfyanonymous
f72780a7e3 The new smart memory management makes this unnecessary. 2023-08-25 18:02:15 -04:00
comfyanonymous
c77f02e1c6 Move controlnet code to comfy/controlnet.py 2023-08-25 17:33:04 -04:00
comfyanonymous
15a7716fa6 Move lora code to comfy/lora.py 2023-08-25 17:11:51 -04:00
doctorpangloss
3a56b15bc2 use comfyui.custom_nodes as the plugin entrypoint and fix the protocol 2023-08-24 22:23:12 -07:00
comfyanonymous
ec96f6d03a Move text_projection to base clip model. 2023-08-24 23:43:48 -04:00
comfyanonymous
30eb92c3cb Code cleanups. 2023-08-24 19:39:18 -04:00
comfyanonymous
51dde87e97 Try to free enough vram for control lora inference. 2023-08-24 17:20:54 -04:00
comfyanonymous
e3d0a9a490 Fix potential issue with text projection matrix multiplication. 2023-08-24 00:54:16 -04:00
comfyanonymous
cc44ade79e Always shift text encoder to GPU when the device supports fp16. 2023-08-23 21:45:00 -04:00
comfyanonymous
a6ef08a46a Even with forced fp16 the cpu device should never use it. 2023-08-23 21:38:28 -04:00
comfyanonymous
00c0b2c507 Initialize text encoder to target dtype. 2023-08-23 21:01:15 -04:00
Benjamin Berman
e9365c4678 wip 2023-08-23 16:14:12 -07:00
comfyanonymous
f081017c1a Save memory by storing text encoder weights in fp16 in most situations. 
Do inference in fp32 to make sure quality stays the exact same.
 2023-08-23 01:08:51 -04:00
Benjamin Berman
b98e1c0f01 move this back since the issue is resolved 2023-08-22 18:00:18 -07:00
comfyanonymous
afcb9cb1df All resolutions now work with t2i adapter for SDXL. 2023-08-22 16:23:54 -04:00
Benjamin Berman
cc215a0658 Merge branch 'master' of https://github.com/comfyanonymous/ComfyUI 2023-08-22 12:16:59 -07:00
Benjamin Berman
2ed2f86117 comfy_extras should not be its own toplevel package 2023-08-22 12:15:57 -07:00
comfyanonymous
85fde89d7f T2I adapter SDXL. 2023-08-22 14:40:43 -04:00
Benjamin Berman
d25d5e75f0 wip make package structure coherent 2023-08-22 11:35:20 -07:00
comfyanonymous
cf5ae46928 Controlnet/t2iadapter cleanup. 2023-08-22 01:06:26 -04:00
comfyanonymous
763b0cf024 Fix control lora not working in fp32. 2023-08-21 20:38:31 -04:00
doombubbles
bc4e52f790 Hash consistency fixes 2023-08-21 13:28:25 -07:00
Benjamin Berman
30ed9fc143 merge with upstream 2023-08-21 12:00:59 -07:00
Benjamin Berman
cff13ace64 node tweaks 2023-08-21 11:44:51 -07:00
comfyanonymous
199d73364a Fix ControlLora on lowvram. 2023-08-21 00:54:04 -04:00
comfyanonymous
d08e53de2e Remove autocast from controlnet code. 2023-08-20 21:47:32 -04:00
comfyanonymous
0d7b0a4dc7 Small cleanups. 2023-08-20 14:56:47 -04:00
Simon Lui
9225465975 Further tuning and fix mem_free_total. 2023-08-20 14:19:53 -04:00
Simon Lui
2c096e4260 Add ipex optimize and other enhancements for Intel GPUs based on recent memory changes. 2023-08-20 14:19:51 -04:00
comfyanonymous
e9469e732d --disable-smart-memory now disables loading model directly to vram. 2023-08-20 04:00:53 -04:00
comfyanonymous
c9b562aed1 Free more memory before VAE encode/decode. 2023-08-19 12:13:13 -04:00
comfyanonymous
b80c3276dc Fix issue with gligen. 2023-08-18 16:32:23 -04:00
comfyanonymous
d6e4b342e6 Support for Control Loras. 
Control loras are controlnets where some of the weights are stored in
"lora" format: an up and a down low rank matrice that when multiplied
together and added to the unet weight give the controlnet weight.

This allows a much smaller memory footprint depending on the rank of the
matrices.

These controlnets are used just like regular ones.
 2023-08-18 11:59:51 -04:00
comfyanonymous
39ac856a33 ReVision support: unclip nodes can now be used with SDXL. 2023-08-18 11:59:36 -04:00
comfyanonymous
76d53c4622 Add support for clip g vision model to CLIPVisionLoader. 2023-08-18 11:13:29 -04:00
Alexopus
e59fe0537a
Fix referenced before assignment 
For https://github.com/BlenderNeko/ComfyUI_TiledKSampler/issues/13
 2023-08-17 22:30:07 +02:00
comfyanonymous
be9c5e25bc Fix issue with not freeing enough memory when sampling. 2023-08-17 15:59:56 -04:00
comfyanonymous
ac0758a1a4 Fix bug with lowvram and controlnet advanced node. 2023-08-17 13:38:51 -04:00
comfyanonymous
c28db1f315 Fix potential issues with patching models when saving checkpoints. 2023-08-17 11:07:08 -04:00
comfyanonymous
3aee33b54e Add --disable-smart-memory for those that want the old behaviour. 2023-08-17 03:12:37 -04:00
comfyanonymous
2be2742711 Fix issue with regular torch version. 2023-08-17 01:58:54 -04:00
comfyanonymous
89a0767abf Smarter memory management. 
Try to keep models on the vram when possible.

Better lowvram mode for controlnets.
 2023-08-17 01:06:34 -04:00
comfyanonymous
2c97c30256 Support small diffusers controlnet so both types are now supported. 2023-08-16 12:45:56 -04:00
comfyanonymous
53f326a3d8 Support diffusers mini controlnets. 2023-08-16 12:28:01 -04:00
comfyanonymous
58f0c616ed Fix clip vision issue with old transformers versions. 2023-08-16 11:36:22 -04:00
comfyanonymous
ae270f79bc Fix potential issue with batch size and clip vision. 2023-08-16 11:05:11 -04:00
Benjamin Berman
0fb47ea4f5 Merge branch 'installable' into spellsource 2023-08-15 17:40:48 -07:00
Benjamin Berman
497c01fed1 fix history 2023-08-15 17:36:56 -07:00
Benjamin Berman
625134b6a1 merge with upstream 2023-08-15 17:13:55 -07:00
comfyanonymous
a2ce9655ca Refactor unclip code. 2023-08-14 23:48:47 -04:00
comfyanonymous
9cc12c833d CLIPVisionEncode can now encode multiple images. 2023-08-14 16:54:05 -04:00
comfyanonymous
0cb6dac943 Remove 3m from PR #1213 because of some small issues. 2023-08-14 00:48:45 -04:00
comfyanonymous
e244b2df83 Add sgm_uniform scheduler that acts like the default one in sgm. 2023-08-14 00:29:03 -04:00
comfyanonymous
58c7da3665 Gpu variant of dpmpp_3m_sde. Note: use 3m with exponential or karras. 2023-08-14 00:28:50 -04:00
comfyanonymous
ba319a34e4 Merge branch 'dpmpp3m' of https://github.com/FizzleDorf/ComfyUI 2023-08-14 00:23:15 -04:00
FizzleDorf
3cfad03a68 dpmpp 3m + dpmpp 3m sde added 2023-08-13 22:29:04 -04:00
comfyanonymous
585a062910 Print unet config when model isn't detected. 2023-08-13 01:39:48 -04:00
Benjamin Berman
894aee44bd fix timestamp issue 2023-08-12 14:30:03 -07:00
Benjamin Berman
87158e6365 example prompt 2023-08-11 18:39:45 -07:00
Benjamin Berman
130378c449 merge upstream 2023-08-11 16:44:16 -07:00
Benjamin Berman
95b630224d fix issues with finding the path to the image file, no matter how the application was started 2023-08-11 15:26:13 -07:00
comfyanonymous
c8a23ce9e8 Support for yet another lora type based on diffusers. 2023-08-11 13:04:21 -04:00
comfyanonymous
2bc12d3d22 Add --temp-directory argument to set temp directory. 2023-08-11 05:13:03 -04:00
comfyanonymous
c20583286f Support diffuser text encoder loras. 2023-08-10 20:28:28 -04:00
comfyanonymous
cf10c5592c Disable calculating uncond when CFG is 1.0 2023-08-09 20:55:03 -04:00
Benjamin Berman
10b8be1c1f fix erroneous sys.version 2023-08-07 17:04:02 -07:00
comfyanonymous
1f0f4cc0bd Add argument to disable auto launching the browser. 2023-08-07 02:25:12 -04:00
comfyanonymous
d8e58f0a7e Detect hint_channels from controlnet. 2023-08-06 14:08:59 -04:00
comfyanonymous
c5d7593ccf Support loras in diffusers format. 2023-08-05 01:40:24 -04:00
Benjamin Berman
3216d1c6b0 fix image upload, running from main 2023-08-04 15:44:02 -07:00
Benjamin Berman
dc4289dbb9 working install from git repo 2023-08-04 15:44:02 -07:00
Benjamin Berman
b12394c9e9 include legacy main.py 2023-08-04 15:44:02 -07:00
Benjamin Berman
3d3c5ae344 wip 2023-08-04 15:44:02 -07:00
Benjamin Berman
82d0edf121 add missing type 2023-08-04 15:44:02 -07:00
Benjamin Berman
b3038de648 make the nodes organization more sane 2023-08-04 15:44:02 -07:00
Benjamin Berman
87cf8f613e mara nodes 2023-08-04 15:44:02 -07:00
Benjamin Berman
66b857d069 basic caching 2023-08-04 15:44:02 -07:00
Benjamin Berman
7c197409be macOS latest with fp16 enabled by default 2023-08-04 15:44:02 -07:00
Benjamin Berman
550788eaca Updates for better compatibility with DeepFloyd 2023-08-04 15:44:02 -07:00
Benjamin Berman
65722c2bb3 openapi definition, documented API endpoints and new ergonomic API endpoint 2023-08-04 15:44:02 -07:00
Benjamin Berman
18d2b23495 Create a setup.py and automatically select the correct pytorch binaries for the current platform and supported devices 
- setup.py now works
 - Makes installation work a variety of ways, including making other packages dependent on this one for e.g. plugins
 - Fixes missing __init__.py issues
 - Fixes imports
 - Compatible with your existing scripts that rely on requirements.txt
 - Fixes error in comfy/ldm/models/diffusion/ddim.py
 - Fixes missing packages for other diffusers code in this repo
 2023-08-04 15:44:02 -07:00
comfyanonymous
1ce0d8ad68 Add CMP 30HX card to the nvidia_16_series list. 2023-08-04 12:08:45 -04:00
comfyanonymous
c99d8002f8 Make sure the pooled output stays at the EOS token with added embeddings. 2023-08-03 20:27:50 -04:00
comfyanonymous
4a77fcd6ab Only shift text encoder to vram when CPU cores are under 8. 2023-07-31 00:08:54 -04:00
comfyanonymous
3cd31d0e24 Lower CPU thread check for running the text encoder on the CPU vs GPU. 2023-07-30 17:18:24 -04:00