comfyanonymous
f019f896c6
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.
2023-11-03 13:13:15 -04:00
comfyanonymous
f10036cbf7
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.
2023-11-01 21:24:08 -04:00
comfyanonymous
ff096742bd
Not used anymore.
2023-11-01 00:01:30 -04:00
comfyanonymous
be85c3408b
Fix some issues with sampling precision.
2023-10-31 23:49:29 -04:00
comfyanonymous
169b76657b
Clean up percent start/end and make controlnets work with sigmas.
2023-10-31 22:14:32 -04:00
comfyanonymous
11e03afad6
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.
2023-10-31 18:11:29 -04:00
comfyanonymous
ab0cfba6d1
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.
2023-10-31 17:33:43 -04:00
comfyanonymous
141c4ffcba
Refactor to make it easier to add custom conds to models.
2023-10-24 23:31:12 -04:00
comfyanonymous
5ee8c5fafc
Sampling code refactor to make it easier to add more conds.
2023-10-24 03:38:41 -04:00
comfyanonymous
370c837794
Fix uni_pc sampler math. This changes the images this sampler produces.
2023-10-20 04:16:53 -04:00
comfyanonymous
f18406d838
Make sure cond_concat is on the right device.
2023-10-19 01:14:25 -04:00
comfyanonymous
516c334a26
Refactor cond_concat into conditioning.
2023-10-18 20:36:58 -04:00
comfyanonymous
5cf44c22ad
Refactor cond_concat into model object.
2023-10-18 16:48:37 -04:00
comfyanonymous
eeadcff352
Add SamplerDPMPP_2M_SDE node.
2023-09-28 21:56:23 -04:00
comfyanonymous
97bd301d8f
Add missing samplers to KSamplerSelect.
2023-09-28 00:17:03 -04:00
comfyanonymous
67a9216de5
Scheduler code refactor.
2023-09-26 17:07:07 -04:00
comfyanonymous
cbeebba747
Sampling code refactor.
2023-09-26 13:45:15 -04:00
comfyanonymous
02f4208e1f
Allow having a different pooled output for each image in a batch.
2023-09-21 01:14:42 -04:00
comfyanonymous
6d227d6fe0
Add cond_or_uncond array to transformer_options so hooks can check what is
...
cond and what is uncond.
2023-09-15 22:21:14 -04:00
comfyanonymous
509dd5ca26
Add DDPM sampler.
2023-09-15 19:22:47 -04:00
comfyanonymous
c40f363254
Allow cancelling of everything with a progress bar.
2023-09-07 23:37:03 -04:00
comfyanonymous
b58288668f
Add a ConditioningSetAreaPercentage node.
2023-09-06 03:28:27 -04:00
comfyanonymous
61036397c8
It doesn't make sense for c_crossattn and c_concat to be lists.
2023-08-31 13:25:00 -04:00
comfyanonymous
280659a6ee
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.
2023-08-18 11:59:51 -04:00
comfyanonymous
a216b56591
Smarter memory management.
...
Try to keep models on the vram when possible.
Better lowvram mode for controlnets.
2023-08-17 01:06:34 -04:00
comfyanonymous
87f1037cf5
Remove 3m from PR #1213 because of some small issues.
2023-08-14 00:48:45 -04:00
comfyanonymous
c3910c4ffb
Add sgm_uniform scheduler that acts like the default one in sgm.
2023-08-14 00:29:03 -04:00
comfyanonymous
c5666c503b
Gpu variant of dpmpp_3m_sde. Note: use 3m with exponential or karras.
2023-08-14 00:28:50 -04:00
FizzleDorf
8b4773ee86
dpmpp 3m + dpmpp 3m sde added
2023-08-13 22:29:04 -04:00
comfyanonymous
1b69a7e7ea
Disable calculating uncond when CFG is 1.0
2023-08-09 20:55:03 -04:00
asagi4
a63268b4e9
Fix timestep ranges when batch_size > 1
2023-07-27 21:14:09 +03:00
comfyanonymous
857a80b857
ControlNetApplyAdvanced can now define when controlnet gets applied.
2023-07-24 17:50:49 -04:00
comfyanonymous
0ed4637a7a
Add a ControlNetApplyAdvanced node.
...
The controlnet can be applied to the positive or negative prompt only by
connecting it correctly.
2023-07-24 13:35:20 -04:00
comfyanonymous
156b047427
Add a way to set which range of timesteps the cond gets applied to.
2023-07-24 09:25:02 -04:00
comfyanonymous
4d83ca88a5
Nodes can now patch the unet function.
2023-07-22 17:01:12 -04:00
comfyanonymous
debccdc6f9
Refactor of sampler code to deal more easily with different model types.
2023-07-17 01:22:12 -04:00
comfyanonymous
4685d2b07f
Merge branch 'condmask-fix' of https://github.com/vmedea/ComfyUI
2023-07-07 01:52:25 -04:00
comfyanonymous
fa8010f038
Disable autocast in unet for increased speed.
2023-07-05 21:58:29 -04:00
comfyanonymous
56d999484b
Add gpu variations of the sde samplers that are less deterministic
...
but faster.
2023-07-05 01:39:38 -04:00
mara
386e66bd7f
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.
2023-07-04 16:34:42 +02:00
comfyanonymous
a098d7e4d2
Set the seed in the SDE samplers to make them more reproducible.
2023-06-25 03:04:57 -04:00
comfyanonymous
a852d8b138
Move latent scale factor from VAE to model.
2023-06-23 02:33:31 -04:00
comfyanonymous
08f1f7686c
Support base SDXL and SDXL refiner models.
...
Large refactor of the model detection and loading code.
2023-06-22 13:03:50 -04:00
comfyanonymous
5384849e5e
Fix k_diffusion math being off by a tiny bit during txt2img.
2023-06-19 15:28:54 -04:00
comfyanonymous
fd8fa51a6d
sampler_cfg_function now uses a dict for the argument.
...
This means arguments can be added without issues.
2023-06-13 16:10:36 -04:00
comfyanonymous
b46c4e51ed
Refactor unCLIP noise augment out of samplers.py
2023-06-11 04:01:18 -04:00
comfyanonymous
1e0ad9564e
Simpler base model code.
2023-06-09 12:31:16 -04:00
comfyanonymous
6dd63b638e
Add DPM-Solver++(2M) SDE and exponential scheduler.
...
exponential scheduler is the one recommended with this sampler.
2023-05-21 01:46:03 -04:00
comfyanonymous
8035000551
Switch default scheduler to normal.
2023-05-15 00:29:56 -04:00
comfyanonymous
ffa3282218
Auto batching improvements.
...
Try batching when cond sizes don't match with smart padding.
2023-05-10 13:59:24 -04:00
