8b60d33bb7
Add ModelSamplingStableCascade to control the shift sampling parameter.
...
shift is 2.0 by default on Stage C and 1.0 by default on Stage B.
9 months ago
667c92814e
Stable Cascade Stage B.
9 months ago
0c9bc19768
Add ImageFromBatch.
9 months ago
20e3da6b31
Add a node to give the controlnet a prompt different from the unet.
9 months ago
f2bae7463e
changed default of LatentBatchSeedBehavior to fixed
10 months ago
7f4725f6b3
Fix some issues with --gpu-only
10 months ago
fc196aac80
Add a LatentBatchSeedBehavior node.
...
This lets you set it so the latents can use the same seed for the sampling
on every image in the batch.
10 months ago
d1533d9c0f
Add experimental photomaker nodes.
...
Put the model file in models/photomaker and use PhotoMakerLoader.
Then use PhotoMakerEncode with the keyword "photomaker" to apply the image
10 months ago
f2d432f9a7
Fix potential turbo scheduler model patching issue.
10 months ago
9fff3c46b4
Move some nodes to model_patches section.
10 months 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.
10 months ago
d4edd9bfa8
Fix hypertile issue with high depths.
10 months ago
b4e915e745
Skip SAG when latent is too small.
10 months ago
2c80d9acb9
Round up to nearest power of 2 in SAG node to fix some resolution issues.
10 months ago
7c9a0f7e0a
Fix BasicScheduler issue with Loras.
11 months ago
35322a3766
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.
11 months ago
8c6493578b
Implement noise augmentation for SD 4X upscale model.
11 months ago
ef4f6037cb
Fix model patches not working in custom sampling scheduler nodes.
11 months 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.
11 months ago
d1f3637a5a
Add a denoise parameter to BasicScheduler node.
11 months ago
6781b181ef
Fix potential tensor device issue with ImageCompositeMasked.
11 months ago
5f54614e7f
Add a RebatchImages node.
11 months ago
e82942cc29
Add a denoise parameter to the SDTurboScheduler.
11 months ago
571ea8cdcc
Fix SAG not working with cfg 1.0
11 months ago
d2f322902c
Fix wrong Stable Zero123 node name.
11 months ago
2258f85159
Support stable zero 123 model.
...
To use it use the ImageOnlyCheckpointLoader to load the checkpoint and
the new Stable_Zero123 node.
11 months ago
a036b94075
Move SaveAnimated nodes to image->animation.
11 months ago
574efd3782
Fix perpneg not working on SDXL.
11 months ago
172984db01
Fix SAG not working on certain resolutions.
11 months ago
6596654d47
Add a LatentBatch node.
11 months ago
adc40e3d7b
Forgot this.
11 months ago
014c8bf2f2
Refactor LCM to support more model types.
11 months ago
9cad2f06ff
Make perp neg take a conditioning input instead of a CLIP one.
11 months ago
574363a8a6
Implement Perp-Neg
11 months ago
a5056cfb1f
Remove useless code.
11 months ago
b12b48e170
cleanup.
11 months ago
ba04a87d10
Refactor and improve the sag node.
...
Moved all the sag related code to comfy_extras/nodes_sag.py
11 months 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
11 months ago
9ac0b487ac
Make --gpu-only put intermediate values in GPU memory instead of cpu.
12 months ago
cdff081023
Fix hypertile.
12 months ago
03eadbb53c
Make HyperTile deterministic
12 months ago
57d7f4464f
Add SDTurboScheduler node.
12 months ago
f30b992b18
.sigma and .timestep now return tensors on the same device as the input.
12 months ago
488de0b4df
ModelSamplingDiscreteLCM -> ModelSamplingDiscreteDistilled
12 months ago
e020ab61f9
Fix output APNG not working with ffmpeg.
12 months ago
8ad5d494d5
Fix APNG not working in ffmpeg.
12 months ago
916e9c998c
Use same default fps as webp node.
12 months ago
eff24ea6aa
Add a node to save animated PNG files. These work in ffpmeg unlike webp.
12 months ago
02ffbb2de3
Fix typo.
12 months 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
12 months ago
comfyanonymous
FizzleDorf
Hari
Rafie Walker
asagi4