1. 10 May, 2024 1 commit
  2. 09 May, 2024 6 commits
  3. 08 May, 2024 7 commits
    • Tolga Cangöz's avatar
      Remove dead code and fix f-string issue (#7720) · c1c42698
      Tolga Cangöz authored
      * Remove dead code
      
      * PylancereportGeneralTypeIssues: Strings nested within an f-string cannot use the same quote character as the f-string prior to Python 3.12.
      
      * Remove dead code
      c1c42698
    • Pierre Dulac's avatar
      Allow users to save SDXL LoRA weights for only one text encoder (#7607) · 75aab346
      Pierre Dulac authored
      
      
      SDXL LoRA weights for text encoders should be decoupled on save
      
      The method checks if at least one of unet, text_encoder and
      text_encoder_2 lora weights are passed, which was not reflected in the
      implentation.
      Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
      Co-authored-by: default avatarYiYi Xu <yixu310@gmail.com>
      75aab346
    • YiYi Xu's avatar
      fix offload test (#7868) · 35358a2d
      YiYi Xu authored
      
      
      fix
      Co-authored-by: default avatarDhruv Nair <dhruv.nair@gmail.com>
      35358a2d
    • Aryan's avatar
      [Pipeline] AnimateDiff SDXL (#6721) · 818f7607
      Aryan authored
      
      
      * update conversion script to handle motion adapter sdxl checkpoint
      
      * add animatediff xl
      
      * handle addition_embed_type
      
      * fix output
      
      * update
      
      * add imports
      
      * make fix-copies
      
      * add decode latents
      
      * update docstrings
      
      * add animatediff sdxl to docs
      
      * remove unnecessary lines
      
      * update example
      
      * add test
      
      * revert conv_in conv_out kernel param
      
      * remove unused param addition_embed_type_num_heads
      
      * latest IPAdapter impl
      
      * make fix-copies
      
      * fix return
      
      * add IPAdapterTesterMixin to tests
      
      * fix return
      
      * revert based on suggestion
      
      * add freeinit
      
      * fix test_to_dtype test
      
      * use StableDiffusionMixin instead of different helper methods
      
      * fix progress bar iterations
      
      * apply suggestions from review
      
      * hardcode flip_sin_to_cos and freq_shift
      
      * make fix-copies
      
      * fix ip adapter implementation
      
      * fix last failing test
      
      * make style
      
      * Update docs/source/en/api/pipelines/animatediff.md
      Co-authored-by: default avatarDhruv Nair <dhruv.nair@gmail.com>
      
      * remove todo
      
      * fix doc-builder errors
      
      ---------
      Co-authored-by: default avatarDhruv Nair <dhruv.nair@gmail.com>
      818f7607
    • Philip Pham's avatar
      Check shape and remove deprecated APIs in scheduling_ddpm_flax.py (#7703) · f29b9348
      Philip Pham authored
      `model_output.shape` may only have rank 1.
      
      There are warnings related to use of random keys.
      
      ```
      tests/schedulers/test_scheduler_flax.py: 13 warnings
        /Users/phillypham/diffusers/src/diffusers/schedulers/scheduling_ddpm_flax.py:268: FutureWarning: normal accepts a single key, but was given a key array of shape (1, 2) != (). Use jax.vmap for batching. In a future JAX version, this will be an error.
          noise = jax.random.normal(split_key, shape=model_output.shape, dtype=self.dtype)
      
      tests/schedulers/test_scheduler_flax.py::FlaxDDPMSchedulerTest::test_betas
        /Users/phillypham/virtualenv/diffusers/lib/python3.9/site-packages/jax/_src/random.py:731: FutureWarning: uniform accepts a single key, but was given a key array of shape (1,) != (). Use jax.vmap for batching. In a future JAX version, this will be an error.
          u = uniform(key, shape, dtype, lo, hi)  # type: ignore[arg-type]
      ```
      f29b9348
    • Tolga Cangöz's avatar
      Fix image upcasting (#7858) · d50baf0c
      Tolga Cangöz authored
      
      
      Fix image's upcasting before `vae.encode()` when using `fp16`
      Co-authored-by: default avatarYiYi Xu <yixu310@gmail.com>
      d50baf0c
    • Hyoungwon Cho's avatar
      Modification on the PAG community pipeline (re) (#7876) · c2217142
      Hyoungwon Cho authored
      
      
      * edited_pag_implementation
      
      * update
      
      ---------
      Co-authored-by: default avataryiyixuxu <yixu310@gmail.com>
      c2217142
  4. 07 May, 2024 2 commits
  5. 06 May, 2024 2 commits
  6. 03 May, 2024 5 commits
  7. 02 May, 2024 8 commits
  8. 01 May, 2024 4 commits
  9. 30 Apr, 2024 5 commits
    • Steven Liu's avatar
      [docs] Community pipelines (#7819) · 0d083702
      Steven Liu authored
      * community pipelines
      
      * feedback
      
      * consolidate
      0d083702
    • Tolga Cangöz's avatar
      Fix CPU offload in docstring (#7827) · b8ccb462
      Tolga Cangöz authored
      Fix cpu offload
      b8ccb462
    • Dhruv Nair's avatar
      SSH Runner Workflow Update (#7822) · 725ead2f
      Dhruv Nair authored
      * add debug workflow
      
      * update
      725ead2f
    • Linoy Tsaban's avatar
      Add B-Lora training option to the advanced dreambooth lora script (#7741) · 26a7851e
      Linoy Tsaban authored
      
      
      * add blora
      
      * add blora
      
      * add blora
      
      * add blora
      
      * little changes
      
      * little changes
      
      * remove redundancies
      
      * fixes
      
      * add B LoRA to readme
      
      * style
      
      * inference
      
      * defaults + path to loras+ generation
      
      * minor changes
      
      * style
      
      * minor changes
      
      * minor changes
      
      * blora arg
      
      * added --lora_unet_blocks
      
      * style
      
      * Update examples/advanced_diffusion_training/README.md
      Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
      
      * add commit hash to B-LoRA repo cloneing
      
      * change inference, remove cloning
      
      * change inference, remove cloning
      add section about configureable unet blocks
      
      * change inference, remove cloning
      add section about configureable unet blocks
      
      * Apply suggestions from code review
      
      ---------
      Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
      26a7851e
    • Sayak Paul's avatar
      [Core] introduce _no_split_modules to `ModelMixin` (#6396) · 3fd31eef
      Sayak Paul authored
      * introduce _no_split_modules.
      
      * unnecessary spaces.
      
      * remove unnecessary kwargs and style
      
      * fix: accelerate imports.
      
      * change to _determine_device_map
      
      * add the blocks that have residual connections.
      
      * add: CrossAttnUpBlock2D
      
      * add: testin
      
      * style
      
      * line-spaces
      
      * quality
      
      * add disk offload test without safetensors.
      
      * checking disk offloading percentages.
      
      * change model split
      
      * add: utility for checking multi-gpu requirement.
      
      * model parallelism test
      
      * splits.
      
      * splits.
      
      * splits
      
      * splits.
      
      * splits.
      
      * splits.
      
      * offload folder to test_disk_offload_with_safetensors
      
      * add _no_split_modules
      
      * fix-copies
      3fd31eef