FazBrowse GitHub Viewer | Trending | | Home

Tools: [Download Repo ZIP] [Original HTTPS Page]

History for src/diffusers/training_utils.py - ModelsLab/diffusers_plus_plus · GitHub

Commits

History for

Commits on Sep 3, 2024

chore: add a cleaning utility to be useful during training. (#9240)
sayakpaul
authored
8ba90aa

Commits on Aug 27, 2024

Replace transformers.deepspeed with transformers.integrations.deepspeed (#9281)

salcc
and
sayakpaul
authored
9aca79f

Commits on Jun 24, 2024

Add extra performance features for EMAModel, torch._foreach operations and better support for non-blocking CPU offloading (#7685)

authored
2ada094

Commits on Jun 18, 2024

[SD3 training] refactor the density and weighting utilities. (#8591)
sayakpaul
authored
4edde13

Commits on Jun 1, 2024

Fix DREAM training (#8302)

authored
bc108e1

Commits on Apr 27, 2024

Add DREAM training (#6381)

AmericanPresidentJimmyCarter
and
Jimmy
authored
9d16daa

Commits on Mar 9, 2024

Add npu support (#7144)
MengqingCao
authored
e6ff752

Commits on Feb 1, 2024

add is_torchvision_available (#6800)

yiyixuxu
and
yiyixuxu
authored
093a03a

Commits on Jan 31, 2024

fix torchvision import (#6796)
patrickvonplaten
authored
c3369f5

Commits on Jan 15, 2024

[Training Utils] create a utility for casting the lora params during training. (#6553)
sayakpaul
authored
a080f0d

Commits on Jan 12, 2024

[Training] fix training resuming problem when using FP16 (SDXL LoRA DreamBooth) (#6514)
sayakpaul
authored
79df503

Commits on Jan 5, 2024

Improve LCM(-LoRA) Distillation Scripts (#6420)
dg845
authored
f3d1333

Commits on Dec 2, 2023

[LoRA serialization] fix: duplicate unet prefix problem. (#5991)

sayakpaul
and
patrickvonplaten
authored
d486f0e

Commits on Oct 11, 2023

[Examples] use loralinear instead of depecrecated lora attn procs. (#5331)
sayakpaul
authored
0fa32bd

Commits on Sep 27, 2023

[Examples] add `compute_snr()` to training utils. (#5188)
sayakpaul
authored
cdcc01b

Commits on Jun 22, 2023

fix: random module seeding (#3846)
sayakpaul
authored
13e781f

Commits on May 22, 2023

Refactor full determinism (#3485)
patrickvonplaten
authored
51843fd

Commits on May 11, 2023

[deepspeed] partial ZeRO-3 support (#3076)

stas00
and
patrickvonplaten
authored
af2a237

Commits on Mar 6, 2023

ema step, don't empty cuda cache (#2563)
williamberman
authored
f727863

Commits on Feb 16, 2023

[Utils] Adds `store()` and `restore()` methods to EMAModel (#2302)

authored
6eaebe8

Commits on Feb 8, 2023

EMA: fix `state_dict()` and `load_state_dict()` & add `cur_decay_value` (#2146)
chenguolin
authored
9d0d070

Commits on Feb 7, 2023

Use `accelerate` save & loading hooks to have better checkpoint structure (#2048)

patrickvonplaten
and
pcuenca
authored
f5ccffe

Commits on Jan 29, 2023

fix typo in EMAModel's load_state_dict() (#2151)
dasayan05
authored
125d783

Commits on Jan 19, 2023

Fix EMA for multi-gpu training in the unconditional example (#1930)

authored
7c82a16

Commits on Jan 2, 2023

updated doc for stable diffusion pipelines (#1770)

authored
da31075

Commits on Jul 28, 2022

[Vae and AutoencoderKL] Final clean of LDM checkpoints (#137)
patrickvonplaten
authored
3100bc9

Commits on Jul 27, 2022

Add training and batched inference test for DDPM vs DDIM (#140)
anton-l
authored
6c15636

Commits on Jul 4, 2022

Commits on Jun 27, 2022

Make style
patrickvonplaten
committed
4261c3a
add EMA during training
anton-l
committed
3f9e3d8

Loading

Back | FazBrowse Home | New Git URL