nodes/city96-ComfyUI_ExtraModels
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
104 Commits 2 Branches 0 Tags
dde1273804b5d624a43ca3eb36e1e4e0db5c89bf
Commit Graph
104 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
junsong dde1273804 fix the conversation and run success; 2024-12-05 00:18:56 -08:00
junsong 81f58d87cd fix the cross-attention num_head bug. 2024-12-04 03:25:35 -08:00
junsong 9ec31c864f first run sucessfull with text encoder mask bug not fix; 2024-11-30 11:50:15 -08:00
junsong 861a378edf sucess add dcae into the repo; 2024-11-30 05:11:01 -08:00
City c6527a45f1 Set t5_attention_mask for new comfy versions 
#79
 2024-10-24 21:00:57 +02:00
City 193c2fd9d3 Remove unused arg 
#80
 2024-08-07 13:42:31 +02:00
City 7e96bf676c Add force offload node 2024-08-02 15:27:46 +02:00
City 6fb8649168 PixArt: fix OneTrainer LoRA 2024-07-27 17:52:02 +02:00
City d89de6e98e Add protobuf to requirements 
#74
 2024-07-17 00:25:46 +02:00
City 1db046de78 PixArt: Update import for SD3 clip 
#76
 2024-07-17 00:22:24 +02:00
a-One-Fan 8cff976421 Intel support for Pixart-Sigma (#64) 
* Fix IPEX attn_drop

* IPEX SDPA 4GB fix

Alchemist GPUs lack the 64 bit emulation needed for >4GB in this case. Attention slicing workaround copied from https://github.com/vladmandic/automatic/blob/master/modules/intel/ipex/attention.py

* Do 4GB fix only when necessary

~20% performance boost to not use the 4GB fix when not necessary

* Move attention.py inside utils

* Better 4GB estimation

* Remove unnecessary warning
 2024-07-06 20:26:29 +02:00
City 40d2a76310 HunYuanDiT: Add 1.2 support 2024-07-04 18:01:53 +02:00
City 62b84531f4 Add ostris/vae-kl-f8-d16 
https://huggingface.co/ostris/vae-kl-f8-d16
 2024-07-02 23:02:31 +02:00
frutiemax92 e866b5b6cb Convert some missing layers (#72) 2024-07-02 01:23:52 +02:00
City faf6979f34 Merge pull request #65 from GavChap/get-depth-programatically 
Get depth programatically
 2024-06-23 22:13:59 +02:00
gchapman 46e4fc8ce3 Add new 900M config for the traditional loader, might be better to have depth selectable? 2024-06-23 19:48:34 +01:00
gchapman 8f42946305 Remove override as the new simple loader works it out for us. 2024-06-23 19:44:32 +01:00
codeMODE 7d0cb8fe31 Merge branch 'city96:main' into get-depth-programatically 2024-06-23 19:43:25 +01:00
gchapman 712f57c915 Use different keys for detection between original model and converted model 2024-06-19 09:45:33 +01:00
City de52d3aa45 PixArt auto checkpoint loader 
Needs better logic for diffusers weights
 2024-06-19 03:03:43 +02:00
City 2ad0b09cb9 PixArt allow on-the-fly PE interpolation 2024-06-19 02:26:01 +02:00
gchapman 91340dedc7 Fix loader depth 2024-06-18 23:56:10 +01:00
gchapman 5b082f424d Revert "Use correct key to get the number of layers, I accidentally used a layer with a 'final' layer giving me an out by one error" 
This reverts commit e43ecbeb64.
 2024-06-18 23:42:08 +01:00
gchapman e43ecbeb64 Use correct key to get the number of layers, I accidentally used a layer with a 'final' layer giving me an out by one error 2024-06-18 23:24:30 +01:00
gchapman 1d6c291e75 Minor optimization to stop a double .to() being needed 2024-06-18 21:45:10 +01:00
gchapman 03a81eddd5 Get the depth of the model by counting layers to allow for models with more depth. This allows for deeper models to be created. Example: https://huggingface.co/ptx0/pixart-reality-mix which is a 900M model 2024-06-18 21:44:42 +01:00
City 5101719ca8 HunYuan config fix 2024-06-16 17:07:18 +02:00
City 9a4629aba7 PixArt SD3 node prompt weight fix 
#61
 2024-06-16 02:51:21 +02:00
City c174662c5b Allow PixArt to use SD3 clip 2024-06-14 16:32:05 +02:00
City 9da9978f6c PixArt LoRA changes 
#60
 2024-06-12 01:04:22 +02:00
City 0f83907911 HunYuanDiT fix double text encoder input 
#58
 2024-05-31 21:56:37 +02:00
City 58ecf66b7a Update README.md 2024-05-29 00:09:58 +02:00
City 7e2db6ee78 HunYuanDiT fix image size cond logic (again) 
#54
 2024-05-28 12:19:38 +02:00
City b773f348e6 HunYuanDiT fix image size cond logic 
#54
 2024-05-28 00:18:44 +02:00
City 014e067483 Update README.md 2024-05-25 18:38:43 +02:00
City 6867aacb26 PixArt fix float64 conversion error 
#48
 2024-05-25 18:09:56 +02:00
City 4946b5038e HunYuanDiT switch to local tokenizer 2024-05-25 17:50:31 +02:00
City 904e5bcacf HunYuanDiT Size cond wrong 2024-05-25 17:44:28 +02:00
City e5c15ba479 HunYuanDiT Fix text encoder device select 
Fixes #47 and #50
 2024-05-25 16:44:58 +02:00
City 1953a3bc99 Update README.md 2024-05-21 23:48:31 +02:00
City 2021226406 Merge pull request #41 from zmwv823/main 
Add MiaoBi
 2024-05-21 23:44:41 +02:00
zmwv823 a443d05ec5 Update README.md 2024-05-21 23:15:18 +08:00
zmwv823 4eebd8636c Update __init__.py 2024-05-21 22:51:55 +08:00
zmwv823 0ff35e1c9e Update README.md 2024-05-21 22:41:56 +08:00
zmwv823 43e933d20b Update 2024-05-21 22:39:05 +08:00
City 13dc46fffc HunYuanDiT missing import 2024-05-21 13:59:42 +02:00
City ea705d06e8 Update README.md 2024-05-20 11:52:48 +02:00
City bad1b65c09 HunYuanDiT Initial proof of concept 
#35
 2024-05-20 11:41:58 +02:00
City 296411cc93 Merge pull request #36 from GavChap/fix-sdp-attention-mask 
* Fix SDP attention mask by creating a diagonal block mask in the right shape.
 2024-05-16 15:46:31 +02:00
gchapman 0f888945f5 * Fix SDP attention mask by creating a diagonal mask in the right shape. 2024-05-16 09:23:16 +01:00