comfyanonymous
cca348a662
Fix BasicScheduler issue with Loras.
2024-01-05 12:31:13 -05:00
comfyanonymous
42aa083379
StableZero123_Conditioning_Batched node.
...
This node lets you generate a batch of images with different elevations or
azimuths by setting the elevation_batch_increment and/or
azimuth_batch_increment.
It also sets the batch index for the latents so that the same init noise is
used on each frame.
2024-01-05 04:20:03 -05:00
comfyanonymous
a36114ce30
Implement noise augmentation for SD 4X upscale model.
2024-01-03 14:27:11 -05:00
comfyanonymous
004cf09984
Fix model patches not working in custom sampling scheduler nodes.
2024-01-03 12:16:30 -05:00
comfyanonymous
7629685d08
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.
2024-01-03 03:37:56 -05:00
comfyanonymous
fe129df5ba
Add a denoise parameter to BasicScheduler node.
2023-12-31 15:37:20 -05:00
comfyanonymous
cae5bede07
Fix potential tensor device issue with ImageCompositeMasked.
2023-12-21 02:35:01 -05:00
comfyanonymous
fcd1d723ac
Add a RebatchImages node.
2023-12-20 16:22:18 -05:00
comfyanonymous
23f97628e1
Add a denoise parameter to the SDTurboScheduler.
2023-12-20 02:54:25 -05:00
comfyanonymous
bf90151704
Fix SAG not working with cfg 1.0
2023-12-18 17:03:32 -05:00
comfyanonymous
a2d5004d23
Fix wrong Stable Zero123 node name.
2023-12-18 03:59:50 -05:00
comfyanonymous
c39ed85f3d
Support stable zero 123 model.
...
To use it use the ImageOnlyCheckpointLoader to load the checkpoint and
the new Stable_Zero123 node.
2023-12-18 03:48:04 -05:00
comfyanonymous
1b16f64d1c
Move SaveAnimated nodes to image->animation.
2023-12-17 02:37:22 -05:00
comfyanonymous
f345c77b3d
Fix perpneg not working on SDXL.
2023-12-16 02:30:16 -05:00
comfyanonymous
73d62af037
Fix SAG not working on certain resolutions.
2023-12-16 01:29:57 -05:00
comfyanonymous
778dd90076
Add a LatentBatch node.
2023-12-16 01:21:00 -05:00
comfyanonymous
6a3d15681b
Forgot this.
2023-12-15 15:46:23 -05:00
comfyanonymous
5adaa97798
Refactor LCM to support more model types.
2023-12-15 15:26:12 -05:00
comfyanonymous
291643cde3
Make perp neg take a conditioning input instead of a CLIP one.
2023-12-15 14:40:57 -05:00
Hari
72500f183b
Implement Perp-Neg
2023-12-16 00:28:16 +05:30
comfyanonymous
99f61f753a
Remove useless code.
2023-12-15 01:28:16 -05:00
comfyanonymous
9f728f9e00
cleanup.
2023-12-14 20:11:46 -05:00
comfyanonymous
b83523b241
Refactor and improve the sag node.
...
Moved all the sag related code to comfy_extras/nodes_sag.py
2023-12-13 16:11:26 -05:00
Rafie Walker
58df1767b4
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
2023-12-13 15:52:11 -05:00
comfyanonymous
63349484b8
Make --gpu-only put intermediate values in GPU memory instead of cpu.
2023-12-08 02:35:45 -05:00
comfyanonymous
d9b51ff370
Fix hypertile.
2023-12-07 15:22:35 -05:00
asagi4
6806b383ad
Make HyperTile deterministic
2023-12-06 21:17:56 +02:00
comfyanonymous
9b85cd696c
Add SDTurboScheduler node.
2023-11-28 13:35:32 -05:00
comfyanonymous
c675a1ba9f
.sigma and .timestep now return tensors on the same device as the input.
2023-11-27 16:41:33 -05:00
comfyanonymous
9e5022a43b
ModelSamplingDiscreteLCM -> ModelSamplingDiscreteDistilled
2023-11-27 16:32:03 -05:00
comfyanonymous
ef7e79ec85
Fix output APNG not working with ffmpeg.
2023-11-24 18:24:19 -05:00
comfyanonymous
3aeca9e72c
Fix APNG not working in ffmpeg.
2023-11-24 18:14:17 -05:00
comfyanonymous
564761ab2a
Use same default fps as webp node.
2023-11-24 11:19:23 -05:00
comfyanonymous
3e33fad53d
Add a node to save animated PNG files. These work in ffpmeg unlike webp.
2023-11-24 11:12:10 -05:00
comfyanonymous
9623e03e9f
Fix typo.
2023-11-23 23:20:07 -05:00
comfyanonymous
838bcaa395
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
2023-11-23 19:48:49 -05:00
comfyanonymous
5e4d60a231
Support SVD img2vid model.
2023-11-23 19:41:33 -05:00
comfyanonymous
6a3d309f7c
Fix SaveAnimatedWEBP not working when metadata is disabled.
2023-11-23 15:39:35 -05:00
comfyanonymous
b55e3ab86b
Add a node to save animated webp.
2023-11-23 14:28:41 -05:00
comfyanonymous
2f876a465b
Allow controlling downscale and upscale methods in PatchModelAddDownscale.
2023-11-22 03:23:16 -05:00
comfyanonymous
87d7fb04b3
Add LatentInterpolate to interpolate between latents.
2023-11-20 03:55:51 -05:00
comfyanonymous
0a37fa8a09
Add a RepeatImageBatch node.
2023-11-19 06:09:01 -05:00
comfyanonymous
476120a5a8
percent_to_sigma now returns a float instead of a tensor.
2023-11-18 23:20:29 -05:00
comfyanonymous
e07971cb86
Add ImageCrop node.
2023-11-18 04:44:17 -05:00
comfyanonymous
7676c8f41a
Make deep shrink behave like it should.
2023-11-16 15:26:28 -05:00
comfyanonymous
d385b8a68d
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.
2023-11-16 13:25:46 -05:00
comfyanonymous
5514c4b8ce
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.
2023-11-16 04:23:44 -05:00
comfyanonymous
702395d4ad
Clean up and refactor sampler code.
...
This should make it much easier to write custom nodes with kdiffusion type
samplers.
2023-11-14 00:39:34 -05:00
comfyanonymous
08143aae10
Reorganize custom_sampling nodes.
2023-11-13 21:45:23 -05:00
comfyanonymous
eb5eefe3c8
Add a node to flip the sigmas for unsampling.
2023-11-13 21:45:08 -05:00
