1d6dd83184
Scheduler code refactor.
1 year ago
446caf711c
Sampling code refactor.
1 year ago
76cdc809bf
Support more controlnet models.
1 year ago
ae87543653
Merge branch 'cast_intel' of https://github.com/simonlui/ComfyUI
1 year ago
eec449ca8e
Allow Intel GPUs to LoRA cast on GPU since it supports BF16 natively.
1 year ago
afa2399f79
Add a way to set output block patches to modify the h and hsp.
1 year ago
492db2de8d
Allow having a different pooled output for each image in a batch.
1 year ago
1cdfb3dba4
Only do the cast on the device if the device supports it.
1 year ago
7c9a92f552
Don't depend on torchvision.
1 year ago
2b6b178173
Added support for lanczos scaling
1 year ago
b92bf8196e
Do lora cast on GPU instead of CPU for higher performance.
1 year ago
321c5fa295
Enable pytorch attention by default on xpu.
1 year ago
61b1f67734
Support models without previews.
1 year ago
43d4935a1d
Add cond_or_uncond array to transformer_options so hooks can check what is
...
cond and what is uncond.
1 year ago
415abb275f
Add DDPM sampler.
1 year ago
94e4fe39d8
This isn't used anywhere.
1 year ago
44361f6344
Support for text encoder models that need attention_mask.
1 year ago
0d8f376446
Set last layer on SD2.x models uses the proper indexes now.
...
Before I had made the last layer the penultimate layer because some
checkpoints don't have them but it's not consistent with the others models.
TLDR: for SD2.x models only: CLIPSetLastLayer -1 is now -2.
1 year ago
0966d3ce82
Don't run text encoders on xpu because there are issues.
1 year ago
3039b08eb1
Only parse command line args when main.py is called.
1 year ago
ed58730658
Don't leave very large hidden states in the clip vision output.
1 year ago
fb3b728203
Fix issue where autocast fp32 CLIP gave different results from regular.
1 year ago
7d401ed1d0
Add ldm format support to UNETLoader.
1 year ago
e85be36bd2
Add a penultimate_hidden_states to the clip vision output.
1 year ago
1e6b67101c
Support diffusers format t2i adapters.
1 year ago
326577d04c
Allow cancelling of everything with a progress bar.
1 year ago
f88f7f413a
Add a ConditioningSetAreaPercentage node.
1 year ago
1938f5c5fe
Add a force argument to soft_empty_cache to force a cache empty.
1 year ago
7746bdf7b0
Merge branch 'generalize_fixes' of https://github.com/simonlui/ComfyUI
1 year ago
2da73b7073
Revert changes in comfy/ldm/modules/diffusionmodules/util.py, which is unused.
2 years ago
a74c5dbf37
Move some functions to utils.py
2 years ago
4a0c4ce4ef
Some fixes to generalize CUDA specific functionality to Intel or other GPUs.
2 years ago
77a176f9e0
Use common function to reshape batch to.
2 years ago
7931ff0fd9
Support SDXL inpaint models.
2 years ago
0e3b641172
Remove xformers related print.
2 years ago
5c363a9d86
Fix controlnet bug.
2 years ago
cfe1c54de8
Fix controlnet issue.
2 years ago
1c012d69af
It doesn't make sense for c_crossattn and c_concat to be lists.
2 years ago
7e941f9f24
Clean up DiffusersLoader node.
2 years ago
18617967e5
Fix error message in model_patcher.py
...
Found while tinkering.
2 years ago
fe4c07400c
Fix "Load Checkpoint with config" node.
2 years ago
f2f5e5dcbb
Support SDXL t2i adapters with 3 channel input.
2 years ago
15adc3699f
Move beta_schedule to model_config and allow disabling unet creation.
2 years ago
bed116a1f9
Remove optimization that caused border.
2 years ago
65cae62c71
No need to check filename extensions to detect shuffle controlnet.
2 years ago
4e89b2c25a
Put clip vision outputs on the CPU.
2 years ago
a094b45c93
Load clipvision model to GPU for faster performance.
2 years ago
1300a1bb4c
Text encoder should initially load on the offload_device not the regular.
2 years ago
f92074b84f
Move ModelPatcher to model_patcher.py
2 years ago
4798cf5a62
Implement loras with norm keys.
2 years ago
b8c7c770d3
Enable bf16-vae by default on ampere and up.
2 years ago
1c794a2161
Fallback to slice attention if xformers doesn't support the operation.
2 years ago
d935ba50c4
Make --bf16-vae work on torch 2.0
2 years ago
a57b0c797b
Fix lowvram model merging.
2 years ago
f72780a7e3
The new smart memory management makes this unnecessary.
2 years ago
c77f02e1c6
Move controlnet code to comfy/controlnet.py
2 years ago
15a7716fa6
Move lora code to comfy/lora.py
2 years ago
ec96f6d03a
Move text_projection to base clip model.
2 years ago
30eb92c3cb
Code cleanups.
2 years ago
51dde87e97
Try to free enough vram for control lora inference.
2 years ago
e3d0a9a490
Fix potential issue with text projection matrix multiplication.
2 years ago
cc44ade79e
Always shift text encoder to GPU when the device supports fp16.
2 years ago
a6ef08a46a
Even with forced fp16 the cpu device should never use it.
2 years ago
00c0b2c507
Initialize text encoder to target dtype.
2 years ago
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.
2 years ago
afcb9cb1df
All resolutions now work with t2i adapter for SDXL.
2 years ago
85fde89d7f
T2I adapter SDXL.
2 years ago
cf5ae46928
Controlnet/t2iadapter cleanup.
2 years ago
763b0cf024
Fix control lora not working in fp32.
2 years ago
199d73364a
Fix ControlLora on lowvram.
2 years ago
d08e53de2e
Remove autocast from controlnet code.
2 years ago
0d7b0a4dc7
Small cleanups.
2 years ago
9225465975
Further tuning and fix mem_free_total.
2 years ago
2c096e4260
Add ipex optimize and other enhancements for Intel GPUs based on recent memory changes.
2 years ago
e9469e732d
--disable-smart-memory now disables loading model directly to vram.
2 years ago
c9b562aed1
Free more memory before VAE encode/decode.
2 years ago
b80c3276dc
Fix issue with gligen.
2 years ago
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.
2 years ago
39ac856a33
ReVision support: unclip nodes can now be used with SDXL.
2 years ago
76d53c4622
Add support for clip g vision model to CLIPVisionLoader.
2 years ago
e59fe0537a
Fix referenced before assignment
...
For https://github.com/BlenderNeko/ComfyUI_TiledKSampler/issues/13
2 years ago
be9c5e25bc
Fix issue with not freeing enough memory when sampling.
2 years ago
ac0758a1a4
Fix bug with lowvram and controlnet advanced node.
2 years ago
c28db1f315
Fix potential issues with patching models when saving checkpoints.
2 years ago
3aee33b54e
Add --disable-smart-memory for those that want the old behaviour.
2 years ago
2be2742711
Fix issue with regular torch version.
2 years ago
89a0767abf
Smarter memory management.
...
Try to keep models on the vram when possible.
Better lowvram mode for controlnets.
2 years ago
2c97c30256
Support small diffusers controlnet so both types are now supported.
2 years ago
53f326a3d8
Support diffusers mini controlnets.
2 years ago
58f0c616ed
Fix clip vision issue with old transformers versions.
2 years ago
ae270f79bc
Fix potential issue with batch size and clip vision.
2 years ago
a2ce9655ca
Refactor unclip code.
2 years ago
9cc12c833d
CLIPVisionEncode can now encode multiple images.
2 years ago
0cb6dac943
Remove 3m from PR #1213 because of some small issues.
2 years ago
e244b2df83
Add sgm_uniform scheduler that acts like the default one in sgm.
2 years ago
58c7da3665
Gpu variant of dpmpp_3m_sde. Note: use 3m with exponential or karras.
2 years ago
ba319a34e4
Merge branch 'dpmpp3m' of https://github.com/FizzleDorf/ComfyUI
2 years ago
3cfad03a68
dpmpp 3m + dpmpp 3m sde added
2 years ago
585a062910
Print unet config when model isn't detected.
2 years ago
c8a23ce9e8
Support for yet another lora type based on diffusers.
2 years ago
comfyanonymous
Simon Lui
MoonRide303
Alexopus
FizzleDorf