wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-02-10 13:32:36 +08:00
Code Issues Actions 14 Packages Projects Releases Wiki Activity
1,382 Commits 93 Branches 117 Tags 1.3 GiB
39ca2da00c
Commit Graph

1382 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
comfyanonymous
39ca2da00c Fix controlnet bug. 2023-09-01 02:01:08 -04:00
comfyanonymous
a0578c5470 Fix controlnet issue. 2023-08-31 15:16:58 -04:00
comfyanonymous
778c290a67 Fix VAEDecodeTiled minimum. 2023-08-31 14:26:16 -04:00
comfyanonymous
61036397c8 It doesn't make sense for c_crossattn and c_concat to be lists. 2023-08-31 13:25:00 -04:00
comfyanonymous
60ad0ed5af Update litegraph with upstream: middle mouse dragging. 2023-08-31 02:39:34 -04:00
Ridan Vandenbergh
1212d1c377 Remove forced lowercase on embeddings endpoint 2023-08-30 20:48:55 +02:00
comfyanonymous
845faf8e51 Clean up DiffusersLoader node. 2023-08-30 12:57:07 -04:00
Simon Lui
c902fd7505 Fix error message in model_patcher.py 
Found while tinkering.
 2023-08-30 00:25:04 -07:00
comfyanonymous
2c2ba07ff2 Fix "Load Checkpoint with config" node. 2023-08-29 23:58:32 -04:00
comfyanonymous
3ccc42c8d9 Use the GPU for the canny preprocessor when available. 2023-08-29 17:58:40 -04:00
comfyanonymous
f1d6719a51 Add node to convert a specific colour in an image to a mask. 2023-08-29 17:55:42 -04:00
comfyanonymous
0482f057e0 Support SDXL t2i adapters with 3 channel input. 2023-08-29 16:44:57 -04:00
comfyanonymous
21b72ff81b Move beta_schedule to model_config and allow disabling unet creation. 2023-08-29 14:22:53 -04:00
comfyanonymous
e0214644e9 Merge branch 'feat/mute_bypass_nodes_in_group' of https://github.com/M1kep/ComfyUI 2023-08-29 11:33:40 -04:00
comfyanonymous
8beb1d641c Merge branch 'preserve-pnginfo' of https://github.com/chrisgoringe/ComfyUI 2023-08-29 11:32:58 -04:00
comfyanonymous
2ab478346d Remove optimization that caused border. 2023-08-29 11:21:36 -04:00
Chris
85747c8593 check for text attr and save 2023-08-29 18:50:28 +10:00
Chris
e6f3ead6ed copy metadata into modified image 2023-08-29 18:50:28 +10:00
Michael Poutre
646a86c3a9 refactor(ui): Switch statement, and handle other modes in group actions 2023-08-29 00:24:31 -07:00
Michael Poutre
dcfa585baa feat(ui): Add node mode toggles to group context menu 2023-08-28 23:49:25 -07:00
comfyanonymous
c019939b9e Use the same units for tile size in VAEDecodeTiled and VAEEncodeTiled. 2023-08-29 01:51:35 -04:00
comfyanonymous
27f54c5481 Merge branch 'master' of https://github.com/bvhari/ComfyUI 2023-08-29 01:42:00 -04:00
comfyanonymous
5da23d7f05 No need to check filename extensions to detect shuffle controlnet. 2023-08-28 16:49:06 -04:00
comfyanonymous
e4957ff97e Put clip vision outputs on the CPU. 2023-08-28 16:26:11 -04:00
comfyanonymous
256eb57284 Load clipvision model to GPU for faster performance. 2023-08-28 15:29:27 -04:00
comfyanonymous
4fb6163a21 Text encoder should initially load on the offload_device not the regular. 2023-08-28 15:08:45 -04:00
comfyanonymous
201631e61d Move ModelPatcher to model_patcher.py 2023-08-28 14:51:31 -04:00
BVH
719f132e04 Reduce min tile size for encode 2023-08-28 22:39:09 +05:30
comfyanonymous
daae7db069 Implement loras with norm keys. 2023-08-28 11:20:06 -04:00
BVH
c5bd14012a Make tile size in Tiled VAE encode/decode user configurable 2023-08-28 19:57:22 +05:30
Dr.Lt.Data
62a6a05b23 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
ae3f7060d8 Enable bf16-vae by default on ampere and up. 2023-08-27 23:06:19 -04:00
comfyanonymous
6932eda1fb Fallback to slice attention if xformers doesn't support the operation. 2023-08-27 22:24:42 -04:00
comfyanonymous
1b9a6a9599 Make --bf16-vae work on torch 2.0 2023-08-27 21:33:53 -04:00
comfyanonymous
9c880848af Merge branch 'increase_client_max_size' of https://github.com/ramyma/ComfyUI 2023-08-27 13:12:39 -04:00
Dr.Lt.Data
9e14d8a1a6 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
dff4463ecb Increase client_max_size to allow bigger request bodies 2023-08-26 19:48:20 +03:00
comfyanonymous
90bfcef833 Fix lowvram model merging. 2023-08-26 11:52:07 -04:00
comfyanonymous
30d39b387d The new smart memory management makes this unnecessary. 2023-08-25 18:02:15 -04:00
comfyanonymous
a2602fc4f9 Move controlnet code to comfy/controlnet.py 2023-08-25 17:33:04 -04:00
comfyanonymous
7fb8cbb5ac Move lora code to comfy/lora.py 2023-08-25 17:11:51 -04:00
comfyanonymous
145e279e6c Move text_projection to base clip model. 2023-08-24 23:43:48 -04:00
comfyanonymous
4731c0b618 Code cleanups. 2023-08-24 19:39:18 -04:00
comfyanonymous
74d1dfb0ad Try to free enough vram for control lora inference. 2023-08-24 17:20:54 -04:00
comfyanonymous
5dbbb2c93c Fix potential issue with text projection matrix multiplication. 2023-08-24 00:54:16 -04:00
comfyanonymous
e340ef7852 Always shift text encoder to GPU when the device supports fp16. 2023-08-23 21:45:00 -04:00
comfyanonymous
5ef57a983b Even with forced fp16 the cpu device should never use it. 2023-08-23 21:38:28 -04:00
comfyanonymous
1aff0360c3 Initialize text encoder to target dtype. 2023-08-23 21:01:15 -04:00
comfyanonymous
e7fc7fb557 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
e26b2b6fd3 Don't hardcode node names for image upload widget. 2023-08-22 19:41:49 -04:00