3ac5d7941d
Add cfgpp_ud10_ab sampler. ( #15951 )
...
This is the result of an experiment where I asked a LLM to create a better
sampler for the base Anima model and gave it a lot of different things to
try.
I wouldn't call this revolutionary but from my basic testing it seems to be
a bit better than the other samplers at lower steps so I have decided to
include it in ComfyUI.
For best result use it at CFG 2.0 on base Anima. It should also work on
other models but I'm not sure about the optimal parameters.
2026-08-28 15:33:18 -04:00
88fec4b605
Skip creating useless noise in res_multistep sampler. ( #15339 )
2026-08-06 18:17:44 -04:00
8e53f001a4
feat: Support HiDream-O1-Image (CORE-187) ( #13817 )
...
* Initial HiDream01-image support
* Cleanup nodes
* Cleaner handling of empty placeholder models
* Remove snap_to_predefined, prefer tooltip for the trained resolutions
* Add model and block wrappers
* Fix shift tooltip
* Add node to work around the patch tile issue
Experimental, runs multiple passes with the patch grid offset and blends with various different methods.
* Qwen35 vision rotary_pos_emb cast fix
* Fix embedding layout type
* Some small optimizations
* Cleanup, don't need this fallback
* Prefix KV cache, cleanup
Bit of speed, reduce redundant code
* Get rid of redundant custom sampler, refactor noise scaling
Our existing lcm sampler is mathematically same, just added the missing options to it instead and a node to control them. Refactored the noise scaling and fix it for the stochastic samplers, add a generic node to control the initial noise scale.
* Update nodes_hidream_o1.py
* Fix some cache validation cases
* Keep existing sampling params
* Remove redundant video vision path
* Replace some numpy ops with torch
* Fx RoPE index for batch size > 1
* Prefer torch preprocessing
* Rename block_type to be compatible with existing patch nodes
* Fixes and tweaks
2026-05-11 20:35:53 -07:00
ef8f25601a
Add I2V for causal forcing model. ( #13719 )
2026-05-07 18:38:36 -07:00
fed8d5efa6
feat: Auto-regressive video generation (CORE-25) ( #13082 )
2026-05-04 21:01:22 -07:00
2a4328d639
ace15: Use dynamic_vram friendly trange ( #12409 )
...
Factor out the ksampler trange and use it in ACE LLM to prevent the
silent stall at 0 and rate distortion due to first-step model load.
2026-02-11 14:53:42 -05:00
f8acd9c402
Reduce RAM usage, fix VRAM OOMs, and fix Windows shared memory spilling with adaptive model loading ( #11845 )
2026-02-01 01:01:11 -05:00
1e4e342f54
Fix noise with ancestral samplers when inferencing on cpu. ( #11528 )
2025-12-26 22:03:01 -05:00
5d9ad0c6bf
Fix the last step with non-zero sigma in sa_solver ( #11380 )
2025-12-17 13:57:40 -05:00
827bb1512b
Add exp_heun_2_x0 sampler series ( #11360 )
2025-12-16 23:35:43 -05:00
6592bffc60
seeds_2: add phi_2 variant and sampler node ( #11309 )
...
* Add phi_2 solver type to seeds_2
* Add sampler node of seeds_2
2025-12-14 00:03:29 -05:00
1a85483da1
Fix depending on asserts to raise an exception in BatchedBrownianTree and Flash attn module ( #9884 )
...
Correctly handle the case where w0 is passed by kwargs in BatchedBrownianTree
2025-09-15 20:05:03 -04:00
32a627bf1f
SEEDS: update noise decomposition and refactor ( #9633 )
...
- Update the decomposition to reflect interval dependency
- Extract phi computations into functions
- Use torch.lerp for interpolation
2025-08-31 00:01:45 -04:00
3aad339b63
Add DPM++ 2M SDE Heun (RES) sampler ( #9542 )
2025-08-27 19:07:31 -04:00
e729a5cc11
Separate denoised and noise estimation in Euler CFG++ ( #9008 )
...
This will change their behavior with the sampling CONST type.
It also combines euler_cfg_pp and euler_ancestral_cfg_pp into one main function.
2025-07-23 19:47:05 -04:00
aac10ad23a
Add SA-Solver sampler ( #8834 )
2025-07-08 16:17:06 -04:00
f41f323c52
Add the denoising step to several samplers ( #8780 )
2025-07-03 19:20:53 -04:00
b22e97dcfa
Migrate ER-SDE from VE to VP algorithm and add its sampler node ( #8744 )
...
Apply alpha scaling in the algorithm for reverse-time SDE and add custom ER-SDE sampler node for other solver types (SDE, ODE).
2025-07-01 02:38:52 -04:00
8042eb20c6
Singlestep DPM++ SDE for RF ( #8627 )
...
Refactor the algorithm, and apply alpha scaling.
2025-06-24 14:59:09 -04:00
8e81c507d2
Multistep DPM++ SDE samplers for RF ( #8541 )
...
Include alpha in sampling and minor refactoring
2025-06-16 14:47:10 -04:00
53e8d8193c
Generalize SEEDS samplers ( #8529 )
...
Restore VP algorithm for RF and refactor noise_coeffs and half-logSNR calculations
2025-06-14 16:58:16 -04:00
1b3bf0a5da
Fix res_multistep_ancestral sampler ( #8030 )
2025-05-09 20:14:13 -04:00
c15909bb62
CFG++ for gradient estimation sampler ( #7809 )
2025-04-28 13:51:35 -04:00
e51d9ba5fc
Add SEEDS (stage 2 & 3 DP) sampler ( #7580 )
...
* Add seeds stage 2 & 3 (DP) sampler
* Change the name to SEEDS in comment
2025-04-12 18:36:08 -04:00
fd5297131f
Guard the edge cases of noise term in er_sde ( #7265 )
2025-03-16 06:02:25 -04:00
3fc688aebd
Ensure the extra_args in dpmpp sde series ( #7204 )
2025-03-12 17:28:59 -04:00
01015bff16
Add er_sde sampler ( #7187 )
2025-03-12 02:42:37 -04:00
caeb27c3a5
res_multistep: Fix cfgpp and add ancestral samplers ( #6731 )
2025-02-08 19:39:58 -05:00
e857dd48b8
Add gradient estimation sampler ( #6554 )
2025-01-22 05:29:40 -05:00
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
c78a45685d
Rewrite res_multistep sampler and implement res_multistep_cfg_pp sampler. ( #6462 )
2025-01-14 18:20:06 -05:00
90f349f93d
Add res_multistep sampler from the cosmos code.
...
This sampler should work with all models.
2025-01-12 03:10:07 -05:00
4209edf48d
Make a few more samplers deterministic.
2025-01-07 02:12:32 -05:00
916d1e14a9
Make ancestral samplers more deterministic.
2025-01-06 03:04:32 -05:00
d170292594
Remove some trailing white space.
2024-12-27 18:02:30 -05:00
c1b92b719d
Some optimizations to euler a.
2024-12-03 06:11:52 -05:00
2d5b3e0078
Remove useless code.
2024-12-02 06:49:55 -05:00
8e4118c0de
make dpm_2_ancestral work with rectified flow.
2024-12-01 07:37:41 -05:00
d605677b33
Make euler_ancestral work on flow models (credit: Ashen).
2024-10-25 19:53:44 -04:00
f584758271
Cleanup some useless lines.
2024-10-14 21:02:39 -04:00
479a427a48
Add dpmpp_2m_cfg_pp ( #4992 )
2024-09-24 02:42:56 -04:00
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
9f4daca9d9
Doesn't really make sense for cfg_pp sampler to call regular one.
2024-09-11 02:51:36 -04:00
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
2622c55aff
Automatically use RF variant of dpmpp_2s_ancestral if RF model.
2024-08-18 00:47:25 -04:00
1beb348ee2
dpmpp_2s_ancestral_RF for rectified flow (Flux, SD3 and Auraflow).
2024-08-18 00:33:30 -04:00
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
44947e7ad4
Add DEIS order 3 sampler.
...
Order 4 seems to give bad results.
2024-06-26 22:40:05 -04:00
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
d5efde89b7
Add ipndm_v sampler, works best with the exponential scheduler.
2024-06-20 08:51:49 -04:00
comfyanonymous