chaObserv
630545d273
Merge 7cf6b5101c into 98bdca4cb2
2025-04-10 08:50:37 -04:00
chaObserv
fd5297131f
Guard the edge cases of noise term in er_sde ( #7265 )
2025-03-16 06:02:25 -04:00
chaObserv
7cf6b5101c
Merge branch 'master' into sa_solver
2025-03-16 10:28:26 +08:00
chaObserv
3fc688aebd
Ensure the extra_args in dpmpp sde series ( #7204 )
2025-03-12 17:28:59 -04:00
chaObserv
01015bff16
Add er_sde sampler ( #7187 )
2025-03-12 02:42:37 -04:00
Pam
caeb27c3a5
res_multistep: Fix cfgpp and add ancestral samplers ( #6731 )
2025-02-08 19:39:58 -05:00
chaObserv
e857dd48b8
Add gradient estimation sampler ( #6554 )
2025-01-22 05:29:40 -05:00
chaObserv
b184c091e2
Merge branch 'master' into sa_solver
2025-01-19 18:31:38 +08:00
Sergii Dymchenko
ebf038d4fa
Use torch.special.expm1 ( #6388 )
...
* Use `torch.special.expm1`
This function provides greater precision than `exp(x) - 1` for small values of `x`.
Found with TorchFix https://github.com/pytorch-labs/torchfix/
* Use non-alias
2025-01-19 04:54:32 -05:00
Pam
c78a45685d
Rewrite res_multistep sampler and implement res_multistep_cfg_pp sampler. ( #6462 )
2025-01-14 18:20:06 -05:00
comfyanonymous
90f349f93d
Add res_multistep sampler from the cosmos code.
...
This sampler should work with all models.
2025-01-12 03:10:07 -05:00
comfyanonymous
4209edf48d
Make a few more samplers deterministic.
2025-01-07 02:12:32 -05:00
chaObserv
8d9dc98fba
Remove more space
2025-01-06 19:35:31 +08:00
chaObserv
eb40f9377b
Remove space
2025-01-06 19:31:19 +08:00
chaObserv
8a8327fa73
change to direct return
2025-01-06 18:58:27 +08:00
chaObserv
6b68b61644
Use default_noise_sampler instead
2025-01-06 18:55:29 +08:00
chaObserv
812dc34f46
Merge branch 'comfyanonymous:master' into sa_solver
2025-01-06 18:09:03 +08:00
comfyanonymous
916d1e14a9
Make ancestral samplers more deterministic.
2025-01-06 03:04:32 -05:00
comfyanonymous
d170292594
Remove some trailing white space.
2024-12-27 18:02:30 -05:00
comfyanonymous
c1b92b719d
Some optimizations to euler a.
2024-12-03 06:11:52 -05:00
comfyanonymous
2d5b3e0078
Remove useless code.
2024-12-02 06:49:55 -05:00
comfyanonymous
8e4118c0de
make dpm_2_ancestral work with rectified flow.
2024-12-01 07:37:41 -05:00
chaObserv
c176ad8f50
Clean up and remove modifying zero sigma
2024-10-30 01:16:34 +08:00
chaObserv
70ff03429c
Merge branch 'comfyanonymous:master' into sa_solver
2024-10-30 00:41:46 +08:00
comfyanonymous
d605677b33
Make euler_ancestral work on flow models (credit: Ashen).
2024-10-25 19:53:44 -04:00
comfyanonymous
f584758271
Cleanup some useless lines.
2024-10-14 21:02:39 -04:00
chaObserv
ce0bff9a4b
Merge branch 'master' into sa_solver
2024-10-13 20:44:03 +08:00
chaObserv
479a427a48
Add dpmpp_2m_cfg_pp ( #4992 )
2024-09-24 02:42:56 -04:00
chaObserv
587c93ebff
Start lower_final_step in predictor earlier to stabilize
2024-09-22 18:27:13 +08:00
chaObserv
1782896502
Fix lambda_prev in corrector
2024-09-22 17:08:50 +08:00
chaObserv
92a630e737
Add SA-Solver
2024-09-22 17:08:50 +08:00
yoinked
e7d4782736
add laplace scheduler [2407.03297] ( #4990 )
...
* add laplace scheduler [2407.03297]
* should be here instead lol
* better settings
2024-09-19 23:23:09 -04:00
comfyanonymous
9f4daca9d9
Doesn't really make sense for cfg_pp sampler to call regular one.
2024-09-11 02:51:36 -04:00
yoinked
b5d0f2a908
Add CFG++ to DPM++ 2S Ancestral ( #3871 )
...
* Update sampling.py
* Update samplers.py
* my bad
* "fix" the sampler
* Update samplers.py
* i named it wrong
* minor sampling improvements
mainly using a dynamic rho value (hey this sounds a lot like smea!!!)
* revert rho change
rho? r? its just 1/2
2024-09-11 02:49:44 -04:00
comfyanonymous
2622c55aff
Automatically use RF variant of dpmpp_2s_ancestral if RF model.
2024-08-18 00:47:25 -04:00
Ashen
1beb348ee2
dpmpp_2s_ancestral_RF for rectified flow (Flux, SD3 and Auraflow).
2024-08-18 00:33:30 -04:00
comfyanonymous
05e831697a
Switch to the real cfg++ method in the samplers.
...
The old _pp ones will be updated automatically to the regular ones with 2x
the cfg.
My fault for not checking what the "_pp" samplers actually did.
2024-06-29 11:59:48 -04:00
comfyanonymous
44947e7ad4
Add DEIS order 3 sampler.
...
Order 4 seems to give bad results.
2024-06-26 22:40:05 -04:00
comfyanonymous
69d710e40f
Implement my alternative take on CFG++ as the euler_pp sampler.
...
Add euler_ancestral_pp which is the ancestral version of euler with the
same modification.
2024-06-25 07:41:52 -04:00
comfyanonymous
d5efde89b7
Add ipndm_v sampler, works best with the exponential scheduler.
2024-06-20 08:51:49 -04:00
comfyanonymous
e11052afcf
Add ipndm sampler.
2024-06-19 16:32:30 -04:00
comfyanonymous
f2e844e054
Optimize some unneeded if conditions in the sampling code.
2024-06-15 02:26:19 -04:00
comfyanonymous
f81a6fade8
Fix some edge cases with samplers and arrays with a single sigma.
2024-05-01 17:05:30 -04:00
comfyanonymous
5d875d77fe
Fix regression with lcm not working with batches.
2024-03-20 20:48:54 -04:00
comfyanonymous
150a3e946f
Make LCM sampler use the model noise scaling function.
2024-03-20 01:35:59 -04:00
comfyanonymous
57eea0efbb
heunpp2 sampler.
2023-11-14 23:50:55 -05:00
comfyanonymous
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.
2023-11-09 18:30:22 -05:00
comfyanonymous
415abb275f
Add DDPM sampler.
2023-09-15 19:22:47 -04:00
Alexopus
e59fe0537a
Fix referenced before assignment
...
For https://github.com/BlenderNeko/ComfyUI_TiledKSampler/issues/13
2023-08-17 22:30:07 +02:00
comfyanonymous
0cb6dac943
Remove 3m from PR #1213 because of some small issues.
2023-08-14 00:48:45 -04:00
