qnloft
/
ComfyUI
mirror of https://github.com/comfyanonymous/ComfyUI.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
1,413 Commits 6 Branches 26 Tags 115 MiB
Commit Graph

1413 Commits

Author SHA1 Message Date
comfyanonymous 8ddd081b09 Use the same units for tile size in VAEDecodeTiled and VAEEncodeTiled. 2023-08-29 01:51:35 -04:00
comfyanonymous fbf375f161 Merge branch 'master' of https://github.com/bvhari/ComfyUI 2023-08-29 01:42:00 -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
BVH d86b222fe9
Reduce min tile size for encode 2023-08-28 22:39:09 +05:30
comfyanonymous 4798cf5a62 Implement loras with norm keys. 2023-08-28 11:20:06 -04:00
BVH 9196588088
Make tile size in Tiled VAE encode/decode user configurable 2023-08-28 19:57:22 +05:30
Dr.Lt.Data 0faee1186f
support on prompt event handler (#765) 
Co-authored-by: Lt.Dr.Data <lt.dr.data@gmail.com>
 2023-08-28 00:52:22 -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 412596d325 Merge branch 'increase_client_max_size' of https://github.com/ramyma/ComfyUI 2023-08-27 13:12:39 -04:00
Dr.Lt.Data d9f4922993
fix: cannot disable dynamicPrompts (#1327) 
* fix: cannot disable dynamicPrompts

* indent fix

---------

Co-authored-by: Lt.Dr.Data <lt.dr.data@gmail.com>
 2023-08-27 12:34:24 -04:00
ramyma 0b6cf7a558 Increase client_max_size to allow bigger request bodies 2023-08-26 19:48:20 +03:00
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
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
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
comfyanonymous d7b3b0f8c1 Don't hardcode node names for image upload widget. 2023-08-22 19:41:49 -04:00
comfyanonymous afcb9cb1df All resolutions now work with t2i adapter for SDXL. 2023-08-22 16:23:54 -04:00
comfyanonymous 85fde89d7f T2I adapter SDXL. 2023-08-22 14:40:43 -04:00
comfyanonymous f2a7cc9121 Add control lora links to colab notebook. 2023-08-22 01:55:09 -04:00
comfyanonymous e2256b4087 Add clip_vision_g download command to colab notebook for ReVision. 2023-08-22 01:44:31 -04:00
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
comfyanonymous bc76b3829f Merge branch 'custom-node-js' of https://github.com/pythongosssss/ComfyUI 2023-08-21 00:58:38 -04:00
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
pythongosssss cdaf65ceb1 remove log 2023-08-20 20:01:25 +01:00
comfyanonymous 0d7b0a4dc7 Small cleanups. 2023-08-20 14:56:47 -04:00
pythongosssss 9b1d5a587c Allow loading js extensions without copying to /web folder 2023-08-20 19:55:48 +01:00
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 8ee0473687 Merge branch 'parallel-extensions-load' of https://github.com/NoCrypt/ComfyUI 2023-08-20 14:14:01 -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
ncpt 81ccacaa7c
Make the extensions loads in parallel instead of waiting one by one 2023-08-19 17:36:13 +07:00
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