 drheadandGitHub
|
d52a1e1a22
|
lint
|
2024-06-08 18:56:23 -04:00 |
|
|
drheadandGitHub
|
39a6d5655f
|
patch k_diffusion to_d and strip device from schedulers
|
2024-06-08 18:55:07 -04:00 |
|
|
drheadandGitHub
|
428975e1d3
|
Merge pull request #1 from AUTOMATIC1111/dev
Dev
|
2024-06-08 18:49:44 -04:00 |
|
|
drheadandGitHub
|
58b24eae30
|
Merge branch 'AUTOMATIC1111:master' into patch-3
|
2024-06-08 18:44:46 -04:00 |
|
|
drheadandGitHub
|
feeb6802aa
|
fix case where first step skilled if skip early cond is 0
|
2024-05-18 01:22:31 -04:00 |
|
|
drheadandGitHub
|
cc9ca67664
|
Add transformer forward patch
|
2024-05-17 13:14:26 -04:00 |
|
|
drheadandGitHub
|
53d67088ee
|
Patch timestep embedding to create tensor on-device
|
2024-05-17 12:12:57 -04:00 |
|
|
drheadandGitHub
|
01491d303c
|
Keep sigmas on CPU
|
2024-05-17 10:36:08 -04:00 |
|
|
|
3a215deff2
|
vectorize kl-optimal sigma calculation
Co-authored-by: mamei16 <marcel.1710@live.de>
|
2024-04-28 00:15:58 -04:00 |
|
|
drheadandGitHub
|
029adbe531
|
implement option to skip uncond on all steps below ngms
|
2024-04-23 03:15:56 -04:00 |
|
|
drheadandGitHub
|
33cbbf9f8b
|
add s_min_uncond_all option
|
2024-04-23 03:15:00 -04:00 |
|
|
drheadandGitHub
|
6e9b69a338
|
change skip_early_cond code to use float
|
2024-04-23 03:08:28 -04:00 |
|
|
drheadandGitHub
|
83182d2799
|
change skip early cond option name and to float
|
2024-04-23 03:07:25 -04:00 |
|
|
drheadandGitHub
|
83266205d0
|
Add KL Optimal scheduler
|
2024-04-23 00:09:43 -04:00 |
|
|
drheadandGitHub
|
8016d78a4b
|
add option for early cfg skip
|
2024-04-22 23:42:24 -04:00 |
|
|
drheadandGitHub
|
a1aa0af8a4
|
add code for skipping CFG on early steps
|
2024-04-22 23:38:44 -04:00 |
|
|
drheadandGitHub
|
4dae91a1fe
|
remove alphas cumprod fix from samplers_common
|
2024-02-26 23:46:10 -05:00 |
|
|
drheadandGitHub
|
94f23d00a7
|
move alphas cumprod override out of processing
|
2024-02-26 23:44:58 -05:00 |
|
|
drheadandGitHub
|
e2cd92ea23
|
move refiner fix to sd_models.py
|
2024-02-26 23:43:27 -05:00 |
|
|
drheadandGitHub
|
648f6a8e0c
|
dont need to preserve alphas_cumprod_original
|
2024-02-25 23:28:36 -05:00 |
|
|
drheadandGitHub
|
9c1ece8978
|
Protect alphas_cumprod during refiner switchover
|
2024-02-20 19:23:21 -05:00 |
|
|
drheadandGitHub
|
bf348032bc
|
fix missing arg
|
2024-02-20 16:59:28 -05:00 |
|
|
drheadandGitHub
|
25eeeaa65f
|
Allow refiner to be triggered by model timestep instead of sampling
|
2024-02-20 16:37:29 -05:00 |
|
|
drheadandGitHub
|
09d2e58811
|
Pass sigma to apply_refiner
|
2024-02-20 16:22:40 -05:00 |
|
|
drheadandGitHub
|
f4869f8de3
|
Add compatibility option for refiner switching
|
2024-02-20 16:18:13 -05:00 |
|
|
drheadandGitHub
|
5381405eaa
|
re-derive sqrt alpha bar and sqrt one minus alphabar
This is the only place these values are ever referenced outside of training code so this change is very justifiable and more consistent.
|
2023-12-09 14:09:28 -05:00 |
|
|
drheadandGitHub
|
81c4ddf6eb
|
fix linting
|
2023-12-02 13:11:00 -05:00 |
|
|
drheadandGitHub
|
309a606c2f
|
ensure that original alpha bar always exists
|
2023-12-02 13:07:45 -05:00 |
|
|
drheadandGitHub
|
668ae34e21
|
remove debug print
|
2023-11-29 22:48:31 -05:00 |
|
|
drheadandGitHub
|
6d0a8dcd89
|
Implement zero terminal SNR schedule option
|
2023-11-29 17:42:07 -05:00 |
|
|
drheadandGitHub
|
588a52891d
|
Add options for zero terminal SNR
|
2023-11-29 17:40:23 -05:00 |
|
|
drheadandGitHub
|
b25c126ccd
|
Protect alphas_cumprod from downcasting
|
2023-11-29 17:38:53 -05:00 |
|
