Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Brandon/flux model loading #6739

Merged
merged 113 commits into from
Aug 27, 2024
Merged

Brandon/flux model loading #6739

merged 113 commits into from
Aug 27, 2024

Commits on Aug 26, 2024

  1. Bump diffusers version to include FLUX support.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    5256f26 View commit details
    Browse the repository at this point in the history

  2. Update imports for compatibility with bumped diffusers version.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    562c2cc View commit details
    Browse the repository at this point in the history

  3. Update HF download logic to work for black-forest-labs/FLUX.1-schnell.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    b617631 View commit details
    Browse the repository at this point in the history

  4. First draft of FluxTextToImageInvocation.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    6a068cc View commit details
    Browse the repository at this point in the history

  5. Add sentencepiece dependency for the T5 tokenizer.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    5149a3e View commit details
    Browse the repository at this point in the history

  6. Use the FluxPipeline.encode_prompt() api rather than trying to run th… 

    …e two text encoders separately.
    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    761e49f View commit details
    Browse the repository at this point in the history

  7. Got FLUX schnell working with 8-bit quantization. Still lots of rough… 

    … edges to clean up.
    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    5e1b3e9 View commit details
    Browse the repository at this point in the history

  8. Minor improvements to FLUX workflow.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    e71c7d0 View commit details
    Browse the repository at this point in the history

  9. Make 8-bit quantization save/reload work for the FLUX transformer. Re… 

    …load is still very slow with the current optimum.quanto implementation.
    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    f7753be View commit details
    Browse the repository at this point in the history

  10. Add support for 8-bit quantizatino of the FLUX T5XXL text encoder.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    28654ec View commit details
    Browse the repository at this point in the history

  11. Make float16 inference work with FLUX on 24GB GPU.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    40e9a4e View commit details
    Browse the repository at this point in the history

  12. WIP - experimentation

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    df1ac07 View commit details
    Browse the repository at this point in the history

  13. Make quantized loading fast.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    11279ab View commit details
    Browse the repository at this point in the history

  14. Make quantized loading fast for both T5XXL and FLUX transformer.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    bcb7f8e View commit details
    Browse the repository at this point in the history

  15. Split a FluxTextEncoderInvocation out from the FluxTextToImageInvocat… 

    …ion. This has the advantage that we benfit from automatic caching when the prompt isn't changed.
    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    3f1fbc6 View commit details
    Browse the repository at this point in the history

  16. wip

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    06d35c3 View commit details
    Browse the repository at this point in the history

  17. NF4 loading working... I think.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    b1cf2f5 View commit details
    Browse the repository at this point in the history

  18. NF4 inference working

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    31c8d76 View commit details
    Browse the repository at this point in the history

  19. Clean up NF4 implementation.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    17f5952 View commit details
    Browse the repository at this point in the history

  20. LLM.int8() quantization is working, but still some rough edges to solve.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    52ff3c7 View commit details
    Browse the repository at this point in the history

  21. More improvements for LLM.int8() - not fully tested.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    307a130 View commit details
    Browse the repository at this point in the history

  22. WIP on moving from diffusers to FLUX

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    27f33bb View commit details
    Browse the repository at this point in the history

  23. Setup flux model loading in the UI

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    e157ff3 View commit details
    Browse the repository at this point in the history

  24. Remove changes to v1 workflow

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    6779e03 View commit details
    Browse the repository at this point in the history

  25. Manage quantization of models within the loader

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    4bb3438 View commit details
    Browse the repository at this point in the history

  26. Run Ruff

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    6b0f5f4 View commit details
    Browse the repository at this point in the history

  27. Run Ruff

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    3814cd7 View commit details
    Browse the repository at this point in the history

  28. Some UI cleanup, regenerate schema

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    a6ad70e View commit details
    Browse the repository at this point in the history

  29. Add backend functions and classes for Flux implementation, Update the… 

    … way flux encoders/tokenizers are loaded for prompt encoding, Update way flux vae is loaded
    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    f3096a8 View commit details
    Browse the repository at this point in the history

  30. Run ruff, setup initial text to image node

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    5fc6c28 View commit details
    Browse the repository at this point in the history

  31. Add nf4 bnb quantized format

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    68d28db View commit details
    Browse the repository at this point in the history

  32. Remove unused param on _run_vae_decoding in flux text to image

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    f3ebbe1 View commit details
    Browse the repository at this point in the history

  33. Working inference node with quantized bnb nf4 checkpoint

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    efab4a3 View commit details
    Browse the repository at this point in the history

  34. Install sub directories with folders correctly, ensure consistent dty… 

    …pe of tensors in flux pipeline and vae
    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    95a2d97 View commit details
    Browse the repository at this point in the history

  35. Select dev/schnell based on state dict, use correct max seq len based… 

    … on dev/schnell, and shift in inference, separate vae flux params into separate config
    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    98151ce View commit details
    Browse the repository at this point in the history

  36. Fix FLUX output image clamping. And a few other minor fixes to make i… 

    …nference work with the full bfloat16 FLUX transformer model.
    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    5d7e154 View commit details
    Browse the repository at this point in the history

  37. Add tqdm progress bar to FLUX denoising.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    870ecd3 View commit details
    Browse the repository at this point in the history

  38. Fix support for 8b quantized t5 encoders, update exception messages i… 

    …n flux loaders
    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    24829b9 View commit details
    Browse the repository at this point in the history

  39. Fix styling/lint

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    f36c6d0 View commit details
    Browse the repository at this point in the history

  40. Add t5 encoders and clip embeds to the model manager

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    bebc6d3 View commit details
    Browse the repository at this point in the history

  41. Some cleanup of the tags and description of flux nodes

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    3f845d9 View commit details
    Browse the repository at this point in the history

  42. exclude flux models from main model dropdown

    @brandonrising
    Mary Hipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    8b3e386 View commit details
    Browse the repository at this point in the history

  43. add default workflow for flux t2i

    @brandonrising
    Mary Hipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    35c263a View commit details
    Browse the repository at this point in the history

  44. Rename t5Encoder -> t5_encoder.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    ec360ee View commit details
    Browse the repository at this point in the history

  45. Address minor review comments.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    c822c3d View commit details
    Browse the repository at this point in the history

  46. Update doc string for import_local_model and remove access_token sinc… 

    …e it's only usable for local file paths
    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    19238ed View commit details
    Browse the repository at this point in the history

  47. Switch inheritance class of flux model loaders

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    ede26a7 View commit details
    Browse the repository at this point in the history

  48. Various styling and exception type updates

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    f0408bb View commit details
    Browse the repository at this point in the history

  49. More flux loader cleanup

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    9e888b1 View commit details
    Browse the repository at this point in the history

  50. Remove duplicate log_time(...) function.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    6afb113 View commit details
    Browse the repository at this point in the history

  51. Add docs to the requantize(...) function explaining why it was copied… 

    … from optimum-quanto.
    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    519bf71 View commit details
    Browse the repository at this point in the history

  52. Move requantize.py to the quatnization/ dir.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    c549a49 View commit details
    Browse the repository at this point in the history

  53. update flux_model_loader node to take a T5 encoder from node field in… 

    …stead of hardcoded list, assume all models have been downloaded
    @maryhipp @brandonrising
    maryhipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    41fb09b View commit details
    Browse the repository at this point in the history

  54. add case for clip embed models in probe

    @maryhipp @brandonrising
    maryhipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    c66ccad View commit details
    Browse the repository at this point in the history

  55. add FLUX schnell starter models and submodels as dependenices or adho… 

    …c download options
    @maryhipp @brandonrising
    maryhipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    9020a8a View commit details
    Browse the repository at this point in the history

  56. fix(ui): only exclude flux main models from linear UI dropdown, not m… 

    …odel manager list
    @brandonrising
    Mary Hipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    7264920 View commit details
    Browse the repository at this point in the history

  57. fix(ui): pass base/type when installing models, add flux formats to M… 

    …M badges
    @brandonrising
    Mary Hipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    3fe9582 View commit details
    Browse the repository at this point in the history

  58. feat(ui): create new field for t5 encoder models in nodes

    @brandonrising
    Mary Hipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    24831d4 View commit details
    Browse the repository at this point in the history

  59. tsc and lint fix

    @brandonrising
    Mary Hipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    6899762 View commit details
    Browse the repository at this point in the history

  60. fix schema

    @brandonrising
    Mary Hipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    f67c4da View commit details
    Browse the repository at this point in the history

  61. update default workflow

    @maryhipp @brandonrising
    maryhipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    a04d479 View commit details
    Browse the repository at this point in the history

  62. fix(worker) fix T5 type

    @maryhipp @brandonrising
    maryhipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    192eda7 View commit details
    Browse the repository at this point in the history

  63. add better workflow description

    @maryhipp @brandonrising
    maryhipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    3c861fd View commit details
    Browse the repository at this point in the history

  64. add better workflow name

    @maryhipp @brandonrising
    maryhipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    dcfdc00 View commit details
    Browse the repository at this point in the history

  65. Fix bug in InvokeInt8Params that was causing it to use double the nec… 

    …essary VRAM.
    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    f51dd36 View commit details
    Browse the repository at this point in the history

  66. Update load_flux_model_bnb_llm_int8.py to work with a single-file FLU… 

    …X transformer checkpoint.
    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    3c9811f View commit details
    Browse the repository at this point in the history

  67. Add docs to the quantization scripts.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    9982bc2 View commit details
    Browse the repository at this point in the history

  68. Fix max_seq_len field description.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    c5c60f5 View commit details
    Browse the repository at this point in the history

  69. Remove automatic install of models during flux model loader, remove n… 

    …o longer used import function on context
    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    5f3e325 View commit details
    Browse the repository at this point in the history

  70. Run ruff

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    bc6e1ba View commit details
    Browse the repository at this point in the history

  71. Undo changes to the v2 dir of frontend types

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    407796c View commit details
    Browse the repository at this point in the history

  72. added FLUX dev to starter models

    @maryhipp @brandonrising
    maryhipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    d4ec434 View commit details
    Browse the repository at this point in the history

  73. Don't install bitsandbytes on macOS

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    374dc82 View commit details
    Browse the repository at this point in the history

  74. Attribute black-forest-labs/flux for much of the flux code

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    80a46d2 View commit details
    Browse the repository at this point in the history

  75. Mark FLUX nodes as prototypes.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    5406a2f View commit details
    Browse the repository at this point in the history

  76. Make FLUX get_noise(...) consistent across devices/dtypes.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    c9c4e47 View commit details
    Browse the repository at this point in the history

  77. Tidy is_schnell detection logic.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    22a3b3d View commit details
    Browse the repository at this point in the history

  78. Add comment about incorrect T5 Tokenizer size calculation.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    5307a6f View commit details
    Browse the repository at this point in the history

  79. Rename field positive_prompt -> prompt.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    5e9ef4b View commit details
    Browse the repository at this point in the history

  80. Move prepare_latent_image_patches(...) to sampling.py with all of the… 

    … related FLUX inference code.
    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    0e9f6f7 View commit details
    Browse the repository at this point in the history

  81. Run FLUX VAE decoding in the user's preferred dtype rather than float… 

    …32. Tested, and seems to work well at float16.
    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    b5c937e View commit details
    Browse the repository at this point in the history

  82. Update macos test vm to macOS-14

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    f34a923 View commit details
    Browse the repository at this point in the history

  83. Load and unload clip/t5 encoders and run inference separately in text… 

    … encoding
    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    b8d4630 View commit details
    Browse the repository at this point in the history

  84. Only import bnb quantize file if bitsandbytes is installed

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    a31c02b View commit details
    Browse the repository at this point in the history

  85. Switch flux to using its own conditioning field

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    9899e42 View commit details
    Browse the repository at this point in the history

  86. Add script for quantizing a T5 model.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    cfcd860 View commit details
    Browse the repository at this point in the history

  87. Fixes to the T5XXL quantization script.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    4089ff2 View commit details
    Browse the repository at this point in the history

  88. Update the T5 8-bit quantized starter model to use the BnB LLM.int8()… 

    … variant.
    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    54c48c3 View commit details
    Browse the repository at this point in the history

  89. Remove all references to optimum-quanto and downgrade diffusers.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    5af214b View commit details
    Browse the repository at this point in the history

  90. Update docs for T5 quantization script.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    f4612a9 View commit details
    Browse the repository at this point in the history

  91. Move quantization scripts to a scripts/ subdir.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    18c0ec3 View commit details
    Browse the repository at this point in the history

  92. Downgrade revert torch version after removing optimum-qanto, and othe… 

    …r minor version-related fixes.
    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    098db5c View commit details
    Browse the repository at this point in the history

  93. Update t5 encoder formats to accurately reflect the quantization stra… 

    …tegy and data type
    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    dbdd851 View commit details
    Browse the repository at this point in the history

  94. Switch the CLIP-L start model to use our hosted version - which is mu… 

    …ch smaller.
    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    1d6c83b View commit details
    Browse the repository at this point in the history

  95. Replace swish() with torch.nn.functional.silu(h). They are functional… 

    …ly equivalent, but in my test VAE deconding was ~8% faster after the change.
    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    1413ff9 View commit details
    Browse the repository at this point in the history

  96. Setup scaffolding for in progress images and add ability to cancel th… 

    …e flux node
    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    bd1b37d View commit details
    Browse the repository at this point in the history

  97. Remove dependency on flux config files

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    d159fe6 View commit details
    Browse the repository at this point in the history

  98. ruff

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    877b88e View commit details
    Browse the repository at this point in the history

  99. Remove flux repo dependency

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    ae94e48 View commit details
    Browse the repository at this point in the history

  100. Downgrade accelerate and huggingface-hub deps to original versions.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    f046a38 View commit details
    Browse the repository at this point in the history

  101. ruff format

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    9f6f404 View commit details
    Browse the repository at this point in the history

  102. Remove outdated TODO.

    @RyanJDick @brandonrising
    RyanJDick authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    9a530c7 View commit details
    Browse the repository at this point in the history

  103. Only install starter models if not already installed

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    bb80697 View commit details
    Browse the repository at this point in the history

  104. Remove in progress images until we're able to make the valuable

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    642a953 View commit details
    Browse the repository at this point in the history

  105. Remove no longer used code in the flux denoise function

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    a90d098 View commit details
    Browse the repository at this point in the history

  106. Fix type error in tsc

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    40a3fa5 View commit details
    Browse the repository at this point in the history

  107. Run ruff

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    b9238b6 View commit details
    Browse the repository at this point in the history

  108. Rename params for flux and flux vae, add comments explaining use of t… 

    …he config_path in model config
    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    5a5ca10 View commit details
    Browse the repository at this point in the history

  109. update default workflow for flux

    @brandonrising
    Mary Hipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    bf59ab3 View commit details
    Browse the repository at this point in the history

  110. remove prompt

    @brandonrising
    Mary Hipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    bd2692b View commit details
    Browse the repository at this point in the history

  111. Run ruff

    @brandonrising
    brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    5d42e67 View commit details
    Browse the repository at this point in the history

  112. default workflow: add steps to exposed fields, add more notes

    @brandonrising
    Mary Hipp authored and brandonrising committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    c510234 View commit details
    Browse the repository at this point in the history

  113. Update starter model size estimates.

    @RyanJDick
    RyanJDick committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    3b29bad View commit details
    Browse the repository at this point in the history