97015b6b38
Cleanup.
12 months 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
57eea0efbb
heunpp2 sampler.
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
dd4ba68b6e
Allow different models to estimate memory usage differently.
1 year ago
2c9dba8dc0
sampling_function now has the model object as the argument.
1 year ago
8d80584f6a
Remove useless argument from uni_pc sampler.
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
ae2acfc21b
Don't convert Nan to zero.
...
Converting Nan to zero is a bad idea because it makes it hard to tell when
something went wrong.
1 year ago
d2e27b48f1
sampler_cfg_function now gets the noisy output as argument again.
...
This should make things that use sampler_cfg_function behave like before.
Added an input argument for those that want the denoised output.
This means you can calculate the x0 prediction of the model by doing:
(input - cond) for example.
1 year ago
e73ec8c4da
Not used anymore.
1 year ago
111f1b5255
Fix some issues with sampling precision.
1 year ago
7c0f255de1
Clean up percent start/end and make controlnets work with sigmas.
1 year ago
a268a574fa
Remove a bunch of useless code.
...
DDIM is the same as euler with a small difference in the inpaint code.
DDIM uses randn_like but I set a fixed seed instead.
I'm keeping it in because I'm sure if I remove it people are going to
complain.
1 year ago
1777b54d02
Sampling code changes.
...
apply_model in model_base now returns the denoised output.
This means that sampling_function now computes things on the denoised
output instead of the model output. This should make things more consistent
across current and future models.
1 year ago
036f88c621
Refactor to make it easier to add custom conds to models.
1 year ago
3fce8881ca
Sampling code refactor to make it easier to add more conds.
1 year ago
4185324a1d
Fix uni_pc sampler math. This changes the images this sampler produces.
1 year ago
e6962120c6
Make sure cond_concat is on the right device.
1 year ago
45c972aba8
Refactor cond_concat into conditioning.
1 year ago
782a24fce6
Refactor cond_concat into model object.
1 year ago
66756de100
Add SamplerDPMPP_2M_SDE node.
1 year ago
d234ca558a
Add missing samplers to KSamplerSelect.
1 year ago
1d6dd83184
Scheduler code refactor.
1 year ago
446caf711c
Sampling code refactor.
1 year ago
492db2de8d
Allow having a different pooled output for each image in a batch.
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
326577d04c
Allow cancelling of everything with a progress bar.
1 year ago
f88f7f413a
Add a ConditioningSetAreaPercentage node.
1 year ago
1c012d69af
It doesn't make sense for c_crossattn and c_concat to be lists.
1 year 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.
1 year ago
89a0767abf
Smarter memory management.
...
Try to keep models on the vram when possible.
Better lowvram mode for controlnets.
1 year ago
0cb6dac943
Remove 3m from PR #1213 because of some small issues.
1 year ago
e244b2df83
Add sgm_uniform scheduler that acts like the default one in sgm.
1 year ago
58c7da3665
Gpu variant of dpmpp_3m_sde. Note: use 3m with exponential or karras.
1 year ago
3cfad03a68
dpmpp 3m + dpmpp 3m sde added
1 year ago
cf10c5592c
Disable calculating uncond when CFG is 1.0
1 year ago
1ea4d84691
Fix timestep ranges when batch_size > 1
1 year ago
7ff14b62f8
ControlNetApplyAdvanced can now define when controlnet gets applied.
1 year ago
d191c4f9ed
Add a ControlNetApplyAdvanced node.
...
The controlnet can be applied to the positive or negative prompt only by
connecting it correctly.
1 year ago
0240946ecf
Add a way to set which range of timesteps the cond gets applied to.
1 year ago
67be7eb81d
Nodes can now patch the unet function.
1 year ago
3ded1a3a04
Refactor of sampler code to deal more easily with different model types.
1 year ago
ddc6f12ad5
Disable autocast in unet for increased speed.
1 year ago
e57cba4c61
Add gpu variations of the sde samplers that are less deterministic
...
but faster.
1 year ago
c61a95f9f7
Fix size check for conditioning mask
...
The wrong dimensions were being checked, [1] and [2] are the image size.
not [2] and [3]. This results in an out-of-bounds error if one of them
actually matches.
1 year ago
4eab00e14b
Set the seed in the SDE samplers to make them more reproducible.
1 year ago
8607c2d42d
Move latent scale factor from VAE to model.
1 year ago
comfyanonymous
FizzleDorf
asagi4
mara