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
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
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
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
comfyanonymous
0d7b0a4dc7
Small cleanups.
2023-08-20 14:56:47 -04:00
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
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
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
comfyanonymous
39ac856a33
ReVision support: unclip nodes can now be used with SDXL.
2023-08-18 11:59:36 -04:00
comfyanonymous
76d53c4622
Add support for clip g vision model to CLIPVisionLoader.
2023-08-18 11:13:29 -04:00
Alexopus
e59fe0537a
Fix referenced before assignment
...
For https://github.com/BlenderNeko/ComfyUI_TiledKSampler/issues/13
2023-08-17 22:30:07 +02:00
comfyanonymous
be9c5e25bc
Fix issue with not freeing enough memory when sampling.
2023-08-17 15:59:56 -04:00
comfyanonymous
ac0758a1a4
Fix bug with lowvram and controlnet advanced node.
2023-08-17 13:38:51 -04:00
comfyanonymous
c28db1f315
Fix potential issues with patching models when saving checkpoints.
2023-08-17 11:07:08 -04:00
comfyanonymous
3aee33b54e
Add --disable-smart-memory for those that want the old behaviour.
2023-08-17 03:12:37 -04:00
comfyanonymous
2be2742711
Fix issue with regular torch version.
2023-08-17 01:58:54 -04:00
comfyanonymous
89a0767abf
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
2c97c30256
Support small diffusers controlnet so both types are now supported.
2023-08-16 12:45:56 -04:00
comfyanonymous
53f326a3d8
Support diffusers mini controlnets.
2023-08-16 12:28:01 -04:00
comfyanonymous
58f0c616ed
Fix clip vision issue with old transformers versions.
2023-08-16 11:36:22 -04:00
comfyanonymous
ae270f79bc
Fix potential issue with batch size and clip vision.
2023-08-16 11:05:11 -04:00
comfyanonymous
a2ce9655ca
Refactor unclip code.
2023-08-14 23:48:47 -04:00
comfyanonymous
9cc12c833d
CLIPVisionEncode can now encode multiple images.
2023-08-14 16:54:05 -04:00
comfyanonymous
0cb6dac943
Remove 3m from PR #1213 because of some small issues.
2023-08-14 00:48:45 -04:00
comfyanonymous
e244b2df83
Add sgm_uniform scheduler that acts like the default one in sgm.
2023-08-14 00:29:03 -04:00
comfyanonymous
58c7da3665
Gpu variant of dpmpp_3m_sde. Note: use 3m with exponential or karras.
2023-08-14 00:28:50 -04:00
comfyanonymous
ba319a34e4
Merge branch 'dpmpp3m' of https://github.com/FizzleDorf/ComfyUI
2023-08-14 00:23:15 -04:00
FizzleDorf
3cfad03a68
dpmpp 3m + dpmpp 3m sde added
2023-08-13 22:29:04 -04:00
comfyanonymous
585a062910
Print unet config when model isn't detected.
2023-08-13 01:39:48 -04:00
comfyanonymous
c8a23ce9e8
Support for yet another lora type based on diffusers.
2023-08-11 13:04:21 -04:00
comfyanonymous
2bc12d3d22
Add --temp-directory argument to set temp directory.
2023-08-11 05:13:03 -04:00
comfyanonymous
c20583286f
Support diffuser text encoder loras.
2023-08-10 20:28:28 -04:00
comfyanonymous
cf10c5592c
Disable calculating uncond when CFG is 1.0
2023-08-09 20:55:03 -04:00
comfyanonymous
1f0f4cc0bd
Add argument to disable auto launching the browser.
2023-08-07 02:25:12 -04:00
comfyanonymous
d8e58f0a7e
Detect hint_channels from controlnet.
2023-08-06 14:08:59 -04:00
comfyanonymous
c5d7593ccf
Support loras in diffusers format.
2023-08-05 01:40:24 -04:00
comfyanonymous
1ce0d8ad68
Add CMP 30HX card to the nvidia_16_series list.
2023-08-04 12:08:45 -04:00
comfyanonymous
c99d8002f8
Make sure the pooled output stays at the EOS token with added embeddings.
2023-08-03 20:27:50 -04:00
comfyanonymous
4a77fcd6ab
Only shift text encoder to vram when CPU cores are under 8.
2023-07-31 00:08:54 -04:00
comfyanonymous
3cd31d0e24
Lower CPU thread check for running the text encoder on the CPU vs GPU.
2023-07-30 17:18:24 -04:00
comfyanonymous
2b13939044
Remove some useless code.
2023-07-30 14:13:33 -04:00
comfyanonymous
95d796fc85
Faster VAE loading.
2023-07-29 16:28:30 -04:00
comfyanonymous
4b957a0010
Initialize the unet directly on the target device.
2023-07-29 14:51:56 -04:00
comfyanonymous
c910b4a01c
Remove unused code and torchdiffeq dependency.
2023-07-28 21:32:27 -04:00
