Commit Graph
308 Commits
Author SHA1 Message Date
kijai 895d3b83a4 Update model_loading.py 2024-11-21 03:05:51 +02:00
kijai 276a045a57 use selected load device as LoRA load device too 2024-11-21 02:46:07 +02:00
kijai e52dc36bc5 Update model_loading.py 2024-11-20 21:28:53 +02:00
kijai e5fc7c1bf3 Allow mixing Fun and not fun loras 2024-11-20 21:24:51 +02:00
kijai e187cfe22f Allow loading the "Rewards" LoRAs into 1.5 as well (for what it's worth) 2024-11-20 19:18:40 +02:00
kijai 573150de28 fix Tora when no autocast 2024-11-20 16:41:34 +02:00
kijai b74aa75026 Don't use autocast with fp/bf16 2024-11-20 14:22:10 +02:00
Jukka Seppänen b9f7b6e338 Merge pull request #261 from Dango233/Dango233-patch-1
Fix fused sdpa
2024-11-20 12:37:26 +02:00
Dango233 b31a025673 Fix fused sdpa 2024-11-20 17:40:28 +08:00
kijai ce329e0dce fix T2V 2024-11-20 10:17:11 +02:00
kijai de7e069286 fix noise augment 2024-11-20 02:12:56 +02:00
kijai 5cc570a467 Add start/end percent to image_conds 2024-11-20 02:07:29 +02:00
kijai b9688f3cd2 Add strength parameter for image encode 2024-11-20 01:32:05 +02:00
kijai ecd067260c Add CogVideoX-Fun-V1.1-5b-Control
https://huggingface.co/alibaba-pai/CogVideoX-Fun-V1.1-5b-Control
2024-11-20 01:23:54 +02:00
kijai c9efefe736 Update cogvideox_1_5_5b_I2V_01.json 2024-11-19 20:33:58 +02:00
kijai f7afa7d3be Update cogvideox_1_5_5b_I2V_01.json 2024-11-19 20:33:15 +02:00
kijai ebd6a3a4e8 update workflows to save_output enabled by default 2024-11-19 20:32:30 +02:00
kijai 41a0f33381 Update model_loading.py 2024-11-19 20:27:31 +02:00
kijai 1cfe0835f5 fix GGUF loader 2024-11-19 20:23:47 +02:00
kijai b0eabeba24 fix comfy attention output shape 2024-11-19 20:18:13 +02:00
kijai 822cb4ee1c Update cogvideox_1_5_5b_I2V_01.json 2024-11-19 20:02:22 +02:00
kijai 882faa6dea add comfyui attention mode 2024-11-19 19:55:51 +02:00
kijai cac1f81c51 Update pipeline_cogvideox.py 2024-11-19 19:42:09 +02:00
Jukka Seppänen fc647862b8 Merge pull request #194 from eltociear/patch-1
docs: update readme.md
2024-11-19 19:25:19 +02:00
kijai 516655b689 Update model_loading.py 2024-11-19 19:17:42 +02:00
kijai 67f2f6abb1 Merge branch 'refactor' 2024-11-19 19:16:39 +02:00
kijai feeff366b5 update 2024-11-19 19:06:15 +02:00
kijai 6302e4b668 Allow orbit LoRAs with Fun models as well 2024-11-19 15:49:43 +02:00
kijai f606d745e9 more examples 2024-11-19 15:34:14 +02:00
kijai 128f89c4d2 Update workflows, fix controlnet 2024-11-19 15:23:38 +02:00
kijai a7646c0d6f refactor
- unify all pipelines into one
- unify transformer model into one
- separate VAE
- add single file model loading
2024-11-19 03:04:22 +02:00
kijai 6f9e4ff647 Update custom_cogvideox_transformer_3d.py 2024-11-17 22:23:40 +02:00
kijai e70da23ac2 exclude sageattn from compile 2024-11-17 22:11:32 +02:00
kijai eebdc412f9 fix sageattention 2024-11-17 21:43:53 +02:00
kijai 15aa68c95d update 2024-11-17 00:48:01 +02:00
kijai 4374273138 possible compile fixes 2024-11-16 22:18:12 +02:00
kijai f21432bea1 tile decode by default 2024-11-16 19:36:13 +02:00
kijai bececf0189 some experimental optimizations 2024-11-16 17:32:31 +02:00
kijai 75e98906a3 rotary embed fix
https://github.com/huggingface/diffusers/pull/9877/commits/25a9e1c567f86bf6de538891d9f07c7f155e70af
2024-11-15 02:37:44 +02:00
kijai 832dad94bc flip width/height inputs to the sampler node (finally) 2024-11-14 19:57:38 +02:00
kijai 0bd3da569e code cleanup
codebase getting too bloated:
drop PAB support in favor of FasterCache
drop temporal tilling in favor of FreeNoise
2024-11-14 19:54:52 +02:00
kijai e8a289112f fix VAE scaling (again) 2024-11-13 15:37:45 +02:00
kijai 34b650c785 fun fixes 2024-11-12 19:29:55 +02:00
kijai 7ac2224ec2 Update nodes.py 2024-11-12 11:30:03 +02:00
kijai ba2dbfbeb4 fixes 2024-11-12 11:29:50 +02:00
kijai dac6a2a3ac allow limiting blocks to cache 2024-11-12 08:42:01 +02:00
kijai 0a121dba53 fix FasterCache 2024-11-12 07:39:00 +02:00
kijai 9681c83c1d Update nodes.py 2024-11-12 00:58:00 +02:00
kijai c8772c3aa0 Update nodes.py 2024-11-12 00:53:55 +02:00
kijai db697fea11 Update model_loading.py 2024-11-12 00:22:26 +02:00