1. 11 May, 2023 2 commits
  2. 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
  3. 06 May, 2023 2 commits
  4. 04 May, 2023 1 commit
  5. 03 May, 2023 2 commits
  6. 28 Apr, 2023 4 commits
  7. 27 Apr, 2023 2 commits
  8. 26 Apr, 2023 3 commits
  9. 25 Apr, 2023 1 commit
  10. 22 Apr, 2023 3 commits
  11. 21 Apr, 2023 2 commits
  12. 20 Apr, 2023 3 commits
  13. 19 Apr, 2023 2 commits
  14. 18 Apr, 2023 4 commits
  15. 17 Apr, 2023 1 commit
  16. 14 Apr, 2023 1 commit
  17. 12 Apr, 2023 5 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
    • Patrick von Platen's avatar
      Release: v0.15.0 · e7534542
      Patrick von Platen authored
      e7534542
    • Sayak Paul's avatar
      Fix InstructPix2Pix training in multi-GPU mode (#2978) · 5a7d35e2
      Sayak Paul authored
      * fix: norm group test for UNet3D.
      
      * fix: unet rejig.
      
      * fix: unwrapping when running validation inputs.
      
      * unwrapping the unet too.
      
      * fix: device.
      
      * better unwrapping.
      
      * unwrapping before ema.
      
      * unwrapping.
      5a7d35e2
    • Sayak Paul's avatar
      [Examples] Fix type-casting issue in the ControlNet training script (#2994) · e607a582
      Sayak Paul authored
      * fix: norm group test for UNet3D.
      
      * fix: type-casting issue in controlnet training.
      e607a582
  18. 11 Apr, 2023 1 commit
    • Chanchana Sornsoontorn's avatar
      Fix typo and format BasicTransformerBlock attributes (#2953) · 52c4d32d
      Chanchana Sornsoontorn authored
      * ️chore(train_controlnet) fix typo in logger message
      
      * ️chore(models) refactor modules order; make them the same as calling order
      
      When printing the BasicTransformerBlock to stdout, I think it's crucial that the attributes order are shown in proper order. And also previously the "3. Feed Forward" comment was not making sense. It should have been close to self.ff but it's instead next to self.norm3
      
      * correct many tests
      
      * remove bogus file
      
      * make style
      
      * correct more tests
      
      * finish tests
      
      * fix one more
      
      * make style
      
      * make unclip deterministic
      
      * 
      
      ️chore(models/attention) reorganize comments in BasicTransformerBlock class
      
      ---------
      Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      52c4d32d