9953f22fce
Add --fast argument to enable experimental optimizations.
...
Optimizations that might break things/lower quality will be put behind
this flag first and might be enabled by default in the future.
Currently the only optimization is float8_e4m3fn matrix multiplication on
4000/ADA series Nvidia cards or later. If you have one of these cards you
will see a speed boost when using fp8_e4m3fn flux for example.
6 months ago
e9589d6d92
Add a way to set model dtype and ops from load_checkpoint_guess_config.
7 months ago
b334605a66
Fix OOMs happening in some cases.
...
A cloned model patcher sometimes reported a model was loaded on a device
when it wasn't.
7 months ago
0a6b008117
Fix issue with some custom nodes.
7 months ago
ba9095e5bd
Automatically use fp8 for diffusion model weights if:
...
Checkpoint contains weights in fp8.
There isn't enough memory to load the diffusion model in GPU vram.
7 months ago
ea03c9dcd2
Better per model memory usage estimations.
7 months ago
3a9ee995cf
Tweak regular SD memory formula.
7 months ago
47da42d928
Better Flux vram estimation.
7 months ago
d420bc792a
Tweak the memory usage formulas for Flux and SD.
7 months ago
1589b58d3e
Basic Flux Schnell and Flux Dev model implementation.
7 months ago
a5f4292f9f
Basic hunyuan dit implementation. ( #4102 )
...
* Let tokenizers return weights to be stored in the saved checkpoint.
* Basic hunyuan dit implementation.
* Fix some resolutions not working.
* Support hydit checkpoint save.
* Init with right dtype.
* Switch to optimized attention in pooler.
* Fix black images on hunyuan dit.
7 months ago
9f291d75b3
AuraFlow model implementation.
8 months ago
8ceb5a02a3
Support saving stable audio checkpoint that can be loaded back.
8 months ago
bb1969cab7
Initial support for the stable audio open model.
8 months ago
0ec513d877
Add a --force-channels-last to inference models in channel last mode.
8 months ago
1ddf512fdc
Don't auto convert clip and vae weights to fp16 when saving checkpoint.
9 months ago
694e0b48e0
SD3 better memory usage estimation.
9 months ago
9424522ead
Reuse code.
9 months ago
8c4a9befa7
SD3 Support.
9 months ago
cd07340d96
Typo fix.
10 months ago
1088d1850f
Support for CosXL models.
11 months ago
575acb69e4
IP2P model loading support.
...
This is the code to load the model and inference it with only a text
prompt. This commit does not contain the nodes to properly use it with an
image input.
This supports both the original SD1 instructpix2pix model and the
diffusers SDXL one.
11 months ago
94a5a67c32
Cleanup to support different types of inpaint models.
11 months ago
40e124c6be
SV3D support.
11 months ago
0ed72befe1
Change log levels.
...
Logging level now defaults to info. --verbose sets it to debug.
12 months ago
65397ce601
Replace prints with logging and add --verbose argument.
12 months ago
51df846598
Let conditioning specify custom concat conds.
12 months ago
cb7c3a2921
Allow image_only_indicator to be None.
1 year ago
8daedc5bf2
Auto detect playground v2.5 model.
1 year ago
0d0fbabd1d
Pass pooled CLIP to stage b.
1 year ago
667c92814e
Stable Cascade Stage B.
1 year ago
f83109f09b
Stable Cascade Stage C.
1 year ago
25a4805e51
Add a way to set different conditioning for the controlnet.
1 year ago
4871a36458
Cleanup some unused imports.
1 year ago
d76a04b6ea
Add unfinished ImageOnlyCheckpointSave node to save a SVD checkpoint.
...
This node is unfinished, SVD checkpoints saved with this node will
work with ComfyUI but not with anything else.
1 year ago
2395ae740a
Make unclip more deterministic.
...
Pass a seed argument note that this might make old unclip images different.
1 year ago
10f2609fdd
Add InpaintModelConditioning node.
...
This is an alternative to VAE Encode for inpaint that should work with
lower denoise.
This is a different take on #2501
1 year ago
8c6493578b
Implement noise augmentation for SD 4X upscale model.
1 year ago
a7874d1a8b
Add support for the stable diffusion x4 upscaling model.
...
This is an old model.
Load the checkpoint like a regular one and use the new
SD_4XUpscale_Conditioning node.
1 year ago
36a7953142
Greatly improve lowvram sampling speed by getting rid of accelerate.
...
Let me know if this breaks anything.
1 year ago
8cf1daa108
Fix SDXL area composition sometimes not using the right pooled output.
1 year ago
2258f85159
Support stable zero 123 model.
...
To use it use the ImageOnlyCheckpointLoader to load the checkpoint and
the new Stable_Zero123 node.
1 year ago
3152023fbc
Use inference dtype for unet memory usage estimation.
1 year ago
77755ab8db
Refactor comfy.ops
...
comfy.ops -> comfy.ops.disable_weight_init
This should make it more clear what they actually do.
Some unused code has also been removed.
1 year ago
ba07cb748e
Use faster manual cast for fp8 in unet.
1 year ago
31b0f6f3d8
UNET weights can now be stored in fp8.
...
--fp8_e4m3fn-unet and --fp8_e5m2-unet are the two different formats
supported by pytorch.
1 year ago
61a123a1e0
A different way of handling multiple images passed to SVD.
...
Previously when a list of 3 images [0, 1, 2] was used for a 6 frame video
they were concated like this:
[0, 1, 2, 0, 1, 2]
now they are concated like this:
[0, 0, 1, 1, 2, 2]
1 year ago
13fdee6abf
Try to free memory for both cond+uncond before inference.
1 year ago
be71bb5e13
Tweak memory inference calculations a bit.
1 year ago
871cc20e13
Support SVD img2vid model.
1 year ago
comfyanonymous
comfyanonymous