Commit Graph

144 Commits

Author SHA1 Message Date
comfyanonymous 6ab8cad22e Implement beta sampling scheduler.
It is based on: https://arxiv.org/abs/2407.12173

Add "beta" to the list of schedulers and the BetaSamplingScheduler node.
2024-07-19 18:05:09 -04:00
Extraltodeus f1a01c2c7e
Add sampler_pre_cfg_function (#3979)
* Update samplers.py

* Update model_patcher.py
2024-07-09 16:20:49 -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 a5e6a632f9 Support sampling non 2D latents. 2024-06-10 01:31:09 -04:00
comfyanonymous f81a6fade8 Fix some edge cases with samplers and arrays with a single sigma. 2024-05-01 17:05:30 -04:00
Jedrzej Kosinski 7990ae18c1
Fix error when more cond masks passed in than batch size (#3353) 2024-04-26 12:51:12 -04:00
comfyanonymous 0f5768e038 Fix missing arguments in cfg_function. 2024-04-04 23:38:57 -04:00
comfyanonymous 1a0486bb96 Fix model needing to be loaded on GPU to generate the sigmas. 2024-04-04 22:08:49 -04:00
comfyanonymous c6bd456c45 Make zero denoise a NOP. 2024-04-04 11:41:27 -04:00
comfyanonymous fcfd2bdf8a Small cleanup. 2024-04-04 11:16:49 -04:00
comfyanonymous 0542088ef8 Refactor sampler code for more advanced sampler nodes part 2. 2024-04-04 01:26:41 -04:00
comfyanonymous 57753c964a Refactor sampling code for more advanced sampler nodes. 2024-04-03 22:09:51 -04:00
comfyanonymous e6482fbbfc Refactor calc_cond_uncond_batch into calc_cond_batch.
calc_cond_batch can take an arbitrary amount of cond inputs.

Added a calc_cond_uncond_batch wrapper with a warning so custom nodes
won't break.
2024-04-01 18:07:47 -04:00
comfyanonymous 0624838237 Add inverse noise scaling function. 2024-03-21 14:49:11 -04:00
comfyanonymous f2fe635c9f SamplerDPMAdaptative node to test the different options. 2024-03-15 22:36:10 -04:00
comfyanonymous 2a813c3b09 Switch some more prints to logging. 2024-03-11 16:34:58 -04:00
comfyanonymous 12c1080ebc Simplify differential diffusion code. 2024-03-03 15:34:42 -05:00
Shiimizu 727021bdea
Implement Differential Diffusion (#2876)
* Implement Differential Diffusion

* Cleanup.

* Fix.

* Masks should be applied at full strength.

* Fix colors.

* Register the node.

* Cleaner code.

* Fix issue with getting unipc sampler.

* Adjust thresholds.

* Switch to linear thresholds.

* Only calculate nearest_idx on valid thresholds.
2024-03-03 15:34:13 -05:00
comfyanonymous 00425563c0 Cleanup: Use sampling noise scaling function for inpainting. 2024-03-01 14:24:41 -05:00
comfyanonymous c62e836167 Move noise scaling to object with sampling math. 2024-03-01 12:54:38 -05:00
comfyanonymous d46583ecec Playground V2.5 support with ModelSamplingContinuousEDM node.
Use ModelSamplingContinuousEDM with edm_playground_v2.5 selected.
2024-02-27 15:12:33 -05:00
logtd e1cb93c383 Fix model and cond transformer options merge 2024-02-23 01:19:43 -07:00
comfyanonymous 10847dfafe Cleanup uni_pc inpainting.
This causes some small changes to the uni pc inpainting behavior but it
seems to improve results slightly.
2024-02-23 02:39:35 -05:00
comfyanonymous 7dd352cbd7 Merge branch 'feature_expose_discard_penultimate_sigma' of https://github.com/blepping/ComfyUI 2024-02-11 12:23:30 -05:00
Jedrzej Kosinski f44225fd5f Fix infinite while loop being possible in ddim_scheduler 2024-02-09 17:11:34 -06:00
blepping a352c021ec Allow custom samplers to request discard penultimate sigma 2024-02-08 02:24:23 -07:00
comfyanonymous 89507f8adf Remove some unused imports. 2024-01-25 23:42:37 -05:00
Dr.Lt.Data 05cd00695a
typo fix - calculate_sigmas_scheduler (#2619)
self.scheduler -> scheduler_name

Co-authored-by: Lt.Dr.Data <lt.dr.data@gmail.com>
2024-01-23 03:47:01 -05:00
comfyanonymous 8c6493578b Implement noise augmentation for SD 4X upscale model. 2024-01-03 14:27:11 -05:00
comfyanonymous 9a7619b72d Fix regression with inpaint model. 2023-12-19 02:32:59 -05:00
comfyanonymous 571ea8cdcc Fix SAG not working with cfg 1.0 2023-12-18 17:03:32 -05:00
comfyanonymous 8cf1daa108 Fix SDXL area composition sometimes not using the right pooled output. 2023-12-18 12:54:23 -05:00
Hari 574363a8a6 Implement Perp-Neg 2023-12-16 00:28:16 +05:30
comfyanonymous 329c571993 Improve code legibility. 2023-12-14 11:41:49 -05:00
comfyanonymous 6c5990f7db Fix cfg being calculated more than once if sampler_cfg_function. 2023-12-13 20:28:04 -05:00
comfyanonymous ba04a87d10 Refactor and improve the sag node.
Moved all the sag related code to comfy_extras/nodes_sag.py
2023-12-13 16:11:26 -05:00
Rafie Walker 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
2023-12-13 15:52:11 -05:00
comfyanonymous 97015b6b38 Cleanup. 2023-12-08 16:02:08 -05:00
comfyanonymous 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.
2023-11-16 04:23:44 -05:00
comfyanonymous 57eea0efbb heunpp2 sampler. 2023-11-14 23:50:55 -05:00
comfyanonymous 420beeeb05 Clean up and refactor sampler code.
This should make it much easier to write custom nodes with kdiffusion type
samplers.
2023-11-14 00:39:34 -05:00
comfyanonymous dd4ba68b6e Allow different models to estimate memory usage differently. 2023-11-12 04:03:52 -05:00
comfyanonymous 2c9dba8dc0 sampling_function now has the model object as the argument. 2023-11-12 03:45:10 -05:00
comfyanonymous 8d80584f6a Remove useless argument from uni_pc sampler. 2023-11-12 01:25:33 -05:00
comfyanonymous 58d5d71a93 Working RescaleCFG node.
This was broken because of recent changes so I fixed it and moved it from
the experiments repo.
2023-11-10 20:52:10 -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