Commit Graph

1344 Commits

Author SHA1 Message Date
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
comfyanonymous
ed16480867 All resolutions now work with t2i adapter for SDXL. 2023-08-22 16:23:54 -04:00
comfyanonymous
b168bdf3e5 T2I adapter SDXL. 2023-08-22 14:40:43 -04:00
comfyanonymous
afd37f0f59 Add control lora links to colab notebook. 2023-08-22 01:55:09 -04:00
comfyanonymous
7f4d874c5d Add clip_vision_g download command to colab notebook for ReVision. 2023-08-22 01:44:31 -04:00
comfyanonymous
08af73e450 Controlnet/t2iadapter cleanup. 2023-08-22 01:06:26 -04:00
comfyanonymous
f29b9306fd Fix control lora not working in fp32. 2023-08-21 20:38:31 -04:00
comfyanonymous
0068154e14 Merge branch 'custom-node-js' of https://github.com/pythongosssss/ComfyUI 2023-08-21 00:58:38 -04:00
comfyanonymous
b982fd039e Fix ControlLora on lowvram. 2023-08-21 00:54:04 -04:00
comfyanonymous
819c4a42d3 Remove autocast from controlnet code. 2023-08-20 21:47:32 -04:00
pythongosssss
19c507f8ae remove log 2023-08-20 20:01:25 +01:00
comfyanonymous
37a6cb2649 Small cleanups. 2023-08-20 14:56:47 -04:00
pythongosssss
baf88698e1 Allow loading js extensions without copying to /web folder 2023-08-20 19:55:48 +01:00
Simon Lui
a670a3f848 Further tuning and fix mem_free_total. 2023-08-20 14:19:53 -04:00
Simon Lui
af8959c8a9 Add ipex optimize and other enhancements for Intel GPUs based on recent memory changes. 2023-08-20 14:19:51 -04:00
comfyanonymous
50ae776b44 Merge branch 'parallel-extensions-load' of https://github.com/NoCrypt/ComfyUI 2023-08-20 14:14:01 -04:00
comfyanonymous
56901bd7c6 --disable-smart-memory now disables loading model directly to vram. 2023-08-20 04:00:53 -04:00
comfyanonymous
225a5f9f1f Free more memory before VAE encode/decode. 2023-08-19 12:13:13 -04:00
ncpt
42c8d4981d Make the extensions loads in parallel instead of waiting one by one 2023-08-19 17:36:13 +07:00
comfyanonymous
01a6f9b116 Fix issue with gligen. 2023-08-18 16:32:23 -04:00
comfyanonymous
280659a6ee 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
398390a76f ReVision support: unclip nodes can now be used with SDXL. 2023-08-18 11:59:36 -04:00
comfyanonymous
e246c23708 Add support for clip g vision model to CLIPVisionLoader. 2023-08-18 11:13:29 -04:00
comfyanonymous
1bdbb515b5 Add node to scale image to a total amount of pixels keeping aspect. 2023-08-18 02:32:39 -04:00
comfyanonymous
715aae3125 Merge branch 'add-user-css' of https://github.com/pythongosssss/ComfyUI 2023-08-17 16:41:54 -04:00
comfyanonymous
1a96067568 Update aiohttp in nightly workflow. 2023-08-17 16:41:24 -04:00
Alexopus
a5a8d25943 Fix referenced before assignment
For https://github.com/BlenderNeko/ComfyUI_TiledKSampler/issues/13
2023-08-17 22:30:07 +02:00
comfyanonymous
bcf55c1446 Fix issue with not freeing enough memory when sampling. 2023-08-17 15:59:56 -04:00
comfyanonymous
d8f9334347 Fix bug with lowvram and controlnet advanced node. 2023-08-17 13:38:51 -04:00
comfyanonymous
e075077ad8 Fix potential issues with patching models when saving checkpoints. 2023-08-17 11:07:08 -04:00
pythongosssss
a53e68a569 Allow user customizable css 2023-08-17 13:36:55 +01:00
comfyanonymous
17ee1d6dc0 Merge branch 'add-growmask-node' of https://github.com/coreyryanhanson/ComfyUI 2023-08-17 03:21:20 -04:00
comfyanonymous
21e07337ed Add --disable-smart-memory for those that want the old behaviour. 2023-08-17 03:12:37 -04:00
comfyanonymous
197ab43811 Fix issue with regular torch version. 2023-08-17 01:58:54 -04:00
comfyanonymous
a216b56591 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
e4ffcf2c61 Support small diffusers controlnet so both types are now supported. 2023-08-16 12:45:56 -04:00
comfyanonymous
1a21a2271e Support diffusers mini controlnets. 2023-08-16 12:28:01 -04:00
comfyanonymous
9e0c084148 Fix clip vision issue with old transformers versions. 2023-08-16 11:36:22 -04:00
comfyanonymous
dcbf839d22 Fix potential issue with batch size and clip vision. 2023-08-16 11:05:11 -04:00