172984db01
Fix SAG not working on certain resolutions.
1 year ago
6596654d47
Add a LatentBatch node.
1 year ago
adc40e3d7b
Forgot this.
1 year ago
014c8bf2f2
Refactor LCM to support more model types.
1 year ago
9cad2f06ff
Make perp neg take a conditioning input instead of a CLIP one.
1 year ago
574363a8a6
Implement Perp-Neg
1 year ago
a5056cfb1f
Remove useless code.
1 year ago
b12b48e170
cleanup.
1 year ago
ba04a87d10
Refactor and improve the sag node.
...
Moved all the sag related code to comfy_extras/nodes_sag.py
1 year ago
6761233e9d
Implement Self-Attention Guidance ( #2201 )
...
* First SAG test
* need to put extra options on the model instead of patcher
* no errors and results seem not-broken
* Use @ashen-uncensored formula, which works better!!!
* Fix a crash when using weird resolutions. Remove an unnecessary UNet call
* Improve comments, optimize memory in blur routine
* SAG works with sampler_cfg_function
1 year ago
9ac0b487ac
Make --gpu-only put intermediate values in GPU memory instead of cpu.
1 year ago
cdff081023
Fix hypertile.
1 year ago
03eadbb53c
Make HyperTile deterministic
1 year ago
57d7f4464f
Add SDTurboScheduler node.
1 year ago
f30b992b18
.sigma and .timestep now return tensors on the same device as the input.
1 year ago
488de0b4df
ModelSamplingDiscreteLCM -> ModelSamplingDiscreteDistilled
1 year ago
e020ab61f9
Fix output APNG not working with ffmpeg.
1 year ago
8ad5d494d5
Fix APNG not working in ffmpeg.
1 year ago
916e9c998c
Use same default fps as webp node.
1 year ago
eff24ea6aa
Add a node to save animated PNG files. These work in ffpmeg unlike webp.
1 year ago
02ffbb2de3
Fix typo.
1 year ago
42dfae6331
Nodes to properly use the SDV img2vid checkpoint.
...
The img2vid model is conditioned on clip vision output only which means
there's no CLIP model which is why I added a ImageOnlyCheckpointLoader to
load it. Note that the unClipCheckpointLoader can also load it because it
also has a CLIP_VISION output.
SDV_img2vid_Conditioning is the node used to pass the right conditioning
to the img2vid model.
VideoLinearCFGGuidance applies a linearly decreasing CFG scale to each
video frame from the cfg set in the sampler node to min_cfg.
SDV_img2vid_Conditioning can be found in conditioning->video_models
ImageOnlyCheckpointLoader can be found in loaders->video_models
VideoLinearCFGGuidance can be found in sampling->video_models
1 year ago
871cc20e13
Support SVD img2vid model.
1 year ago
022033a0e7
Fix SaveAnimatedWEBP not working when metadata is disabled.
1 year ago
a657f96c5c
Add a node to save animated webp.
1 year ago
c3ae99a749
Allow controlling downscale and upscale methods in PatchModelAddDownscale.
1 year ago
31c5ea7b2c
Add LatentInterpolate to interpolate between latents.
1 year ago
dba4f3b4fc
Add a RepeatImageBatch node.
1 year ago
d9d8702d8d
percent_to_sigma now returns a float instead of a tensor.
1 year ago
8a451234b3
Add ImageCrop node.
1 year ago
7e3fe3ad28
Make deep shrink behave like it should.
1 year ago
bd07ad1861
Add PatchModelAddDownscale (Kohya Deep Shrink) node.
...
By adding a downscale to the unet in the first timesteps this node lets
you generate images at higher resolutions with less consistency issues.
1 year ago
dcec1047e6
Invert the start and end percentages in the code.
...
This doesn't affect how percentages behave in the frontend but breaks
things if you relied on them in the backend.
percent_to_sigma goes from 0 to 1.0 instead of 1.0 to 0 for less confusion.
Make percent 0 return an extremely large sigma and percent 1.0 return a
zero one to fix imprecision.
1 year ago
420beeeb05
Clean up and refactor sampler code.
...
This should make it much easier to write custom nodes with kdiffusion type
samplers.
1 year ago
8509bd58b4
Reorganize custom_sampling nodes.
1 year ago
61112c81b9
Add a node to flip the sigmas for unsampling.
1 year ago
ca2812bae0
Fix RescaleCFG for batch size > 1.
1 year ago
58d5d71a93
Working RescaleCFG node.
...
This was broken because of recent changes so I fixed it and moved it from
the experiments repo.
1 year ago
002aefa382
Support lcm models.
...
Use the "lcm" sampler to sample them, you also have to use the
ModelSamplingDiscrete node to set them as lcm models to use them properly.
1 year ago
ca71e542d2
Lower cfg step to 0.1 in sampler nodes.
1 year ago
844dbf97a7
Add: advanced->model->ModelSamplingDiscrete node.
...
This allows changing the sampling parameters of the model (eps or vpred)
or set the model to use zsnr.
1 year ago
4acfc11a80
add difference blend mode
1 year ago
ee74ef5c9e
Increase maximum batch size in LatentRebatch.
1 year ago
23c5d17837
Added Bayer dithering to Quantize node.
1 year ago
1443caf373
HyperTile node, can be found in: _for_testing->HyperTile
1 year ago
c2bb34d865
Implement updated FreeU as _for_testing->FreeU_V2 node
1 year ago
f8caa24bcc
Support hypernetwork with mish activation function and layer norm.
1 year ago
b5fa3d28d7
Fix MaskComposite
1 year ago
87097a11c3
Fix FeatherMask
1 year ago
20d3852aa1
Pull some small changes from the other repo.
1 year ago
877553843f
Add a CLIPSave node to save CLIP model weights.
1 year ago
7bb9f6b7e8
Add a VAESave node.
1 year ago
c16f5744e3
Fix SplitImageWithAlpha and JoinImageWithAlpha.
1 year ago
69a824e9a4
Move _for_testing/custom_sampling nodes to sampling/custom_sampling.
1 year ago
0e763e880f
JoinImageWithAlpha now works with any mask shape.
1 year ago
9212bea87c
Change a few things in #1578 .
1 year ago
214ca7197e
Corrected joining images with alpha (for RGBA input), and checking scaling conditions
1 year ago
585fb0475b
Adding default alpha when splitting RGB images
1 year ago
ece69bf28c
Change channel type to MASK (reduced redundancy, increased usability)
1 year ago
d06cd2805d
Added support for Porter-Duff image compositing
1 year ago
2ef459b1d4
Add VPScheduler node
1 year ago
8ab49dc0a4
DPMPP_SDE node.
1 year ago
213976f8c3
Add ExponentialScheduler and PolyexponentialScheduler nodes.
1 year ago
1c8ae9dbb2
Allow GrowMask node to work with batches (for AnimateDiff) ( #1623 )
...
* Allow mask batches
This allows LatentCompositeMasked -node to work with AnimateDiff. I tried to keep old functionality too, unsure if it's correct, but both single mask and batch of masks seems to work with this change.
* Update nodes_mask.py
1 year ago
66756de100
Add SamplerDPMPP_2M_SDE node.
1 year ago
26b7372805
Fix SplitSigmas.
1 year ago
76e0f8fc8f
Add function to split sigmas.
1 year ago
2bf051fda8
Add a basic node to generate sigmas from scheduler.
1 year ago
d234ca558a
Add missing samplers to KSamplerSelect.
1 year ago
1d7dfc07d5
Make add_noise in SamplerCustom a boolean.
1 year ago
1adcc4c3a2
Add a SamplerCustom Node.
...
This node takes a list of sigmas and a sampler object as input.
This lets people easily implement custom schedulers and samplers as nodes.
More nodes will be added to it in the future.
1 year ago
1d36dfb9fe
GrowMask now works with mask batches.
1 year ago
d76d71de3f
GrowMask can now be used with negative numbers to erode it.
1 year ago
d2cec6cdbf
Make mask functions work with batches of masks and images.
1 year ago
046b4fe0ee
Support batches of masks in mask composite nodes.
1 year ago
f00471cdc8
Do FreeU fft on CPU if the device doesn't support fft functions.
1 year ago
05e661e5ef
FreeU now works with the refiner.
1 year ago
fd93c759e2
Implement FreeU: Free Lunch in Diffusion U-Net node.
...
_for_testing->FreeU
1 year ago
29ccf9f471
Fix typo.
1 year ago
422d16c027
Add some nodes to add, subtract and multiply latents.
1 year ago
2b6b178173
Added support for lanczos scaling
1 year ago
0665749b1a
Move ModelSubtract and ModelAdd to advanced/model_merging
1 year ago
30de95e4b4
Add some nodes to subtract and add model weights.
1 year ago
8be46438be
Support DiffBIR SwinIR models.
1 year ago
766c7b3815
Update upscale model code to latest Chainner model code.
...
Don't add SRFormer because the code license is incompatible with the GPL.
Remove MAT because it's unused and the license is incompatible with GPL.
1 year ago
d70b0bc43c
Use the GPU for the canny preprocessor when available.
2 years ago
81d9200e18
Add node to convert a specific colour in an image to a mask.
2 years ago
fc99fa56a9
Add node to scale image to a total amount of pixels keeping aspect.
2 years ago
18e86a4010
add a node to allow growing of masks through dilation
2 years ago
6dc02c7bac
Add a "resize_source" option to Image and Latent CompositeMasked.
2 years ago
94fceb8700
Make Blur node use the image device for processing.
2 years ago
8c730dc4a7
Add an ImageCompositeMasked node.
2 years ago
1141029a4a
Add --disable-metadata argument to disable saving metadata in files.
2 years ago
5e3ac1928a
Implement modelspec metadata in CheckpointSave for SDXL and refiner.
2 years ago
a51f33ee49
Use bigger tiles when upscaling with model and fallback on OOM.
2 years ago
91ed2815d5
Add a node to merge CLIP models.
2 years ago
bdba394290
Add a canny preprocessor node.
2 years ago
a9a4ba7574
Fix merging not working when model2 of model merge node was a merge.
2 years ago
2c9d98f3e6
CLIPTextEncodeSDXL now works when prompts are of very different sizes.
2 years ago
c02f3baeaf
Now the model merge blocks node will use the longest match.
2 years ago
comfyanonymous
Hari
Rafie Walker
asagi4
matt3o
tsone
Jairo Correa
MoonRide303
Jukka Seppänen
Corey