Skip to content

GitLab

Switch branch/tag
  1. 17 May, 2023 2 commits
  3. 16 May, 2023 1 commit
  5. 12 May, 2023 1 commit
  7. 11 May, 2023 2 commits
  9. 09 May, 2023 1 commit
    • Will Berman's avatar
      if dreambooth lora (#3360) · a757b2db
      Will Berman authored 
      * update IF stage I pipelines

add fixed variance schedulers and lora loading

* added kv lora attn processor

* allow loading into alternative lora attn processor

* make vae optional

* throw away predicted variance

* allow loading into added kv lora layer

* allow load T5

* allow pre compute text embeddings

* set new variance type in schedulers

* fix copies

* refactor all prompt embedding code

class prompts are now included in pre-encoding code
max tokenizer length is now configurable
embedding attention mask is now configurable

* fix for when variance type is not defined on scheduler

* do not pre compute validation prompt if not present

* add example test for if lora dreambooth

* add check for train text encoder and pre compute text embeddings
      a757b2db
  11. 06 May, 2023 2 commits
  13. 04 May, 2023 1 commit
  15. 03 May, 2023 2 commits
  17. 28 Apr, 2023 4 commits
  19. 27 Apr, 2023 2 commits
  21. 26 Apr, 2023 3 commits
  23. 25 Apr, 2023 1 commit
  25. 22 Apr, 2023 3 commits
  27. 21 Apr, 2023 2 commits
  29. 20 Apr, 2023 3 commits
  31. 19 Apr, 2023 2 commits
  33. 18 Apr, 2023 4 commits
  35. 17 Apr, 2023 1 commit
  37. 14 Apr, 2023 1 commit
  39. 12 Apr, 2023 2 commits
    • Andreas Steiner's avatar
      Adds profiling flags, computes train metrics average. (#3053) · d06e0694
      Andreas Steiner authored 
      * WIP controlnet training

- bugfix --streaming
- bugfix running report_to!='wandb'
- adds memory profile before validation

* Adds final logging statement.

* Sets train epochs to 11.

Looking at a longer ~16ep run, we see only good validation images
after ~11ep:

https://wandb.ai/andsteing/controlnet_fill50k/runs/3j2hx6n8



* Removes --logging_dir (it's not used).

* Adds --profile flags.

* Updates --output_dir=runs/fill-circle-{timestamp}.

* Compute mean of `train_metrics`.

Previously `train_metrics[-1]` was logged, resulting in very bumpy train
metrics.

* Improves logging a bit.

- adds l2_grads gradient norm logging
- adds steps_per_sec
- sets walltime as x coordinate of train/step
- logs controlnet_params config

* Adds --ccache (doesn't really help though).

* minor fix in controlnet flax example (#2986)

* fix the error when push_to_hub but not log validation

* contronet_from_pt & controlnet_revision

* add intermediate checkpointing to the guide

* Bugfix --profile_steps

* Sets `RACKER_PROJECT_NAME='controlnet_fill50k'`.

* Logs fractional epoch.

* Adds relative `walltime` metric.

* Adds `StepTraceAnnotation` and uses `global_step` insetad of `step`.

* Applied `black`.

* Streamlines commands in README a bit.

* Removes `--ccache`.

This makes only a very small difference (~1 min) with this model size, so removing
the option introduced in cdb3cc.

* Re-ran `black`.

* Update examples/controlnet/README.md
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>

* Converts spaces to tab.

* Removes repeated args.

* Skips first step (compilation) in profiling

* Updates README with profiling instructions.

* Unifies tabs/spaces in README.

* Re-ran style & quality.

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
      d06e0694
    • Patrick von Platen's avatar
      [Post release] v0.16.0dev (#3072) · 0a73b4d3
      Patrick von Platen authored
      0a73b4d3