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

Add FLUX image-to-image and inpainting #6798

Merged
merged 20 commits into from
Sep 2, 2024
Merged

Add FLUX image-to-image and inpainting #6798

merged 20 commits into from
Sep 2, 2024

Commits on Sep 2, 2024

  1. Add FLUX VAE support to ImageToLatentsInvocation.

    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    e85c3bc View commit details
    Browse the repository at this point in the history

  2. Add FLUX VAE decoding support to LatentsToImageInvocation.

    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    ffa3985 View commit details
    Browse the repository at this point in the history

  3. Get FLUX non-masked image-to-image working - still rough.

    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    a7a33d7 View commit details
    Browse the repository at this point in the history

  4. Split VAE decoding out from the FLUXTextToImageInvocation.

    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    0aa13c0 View commit details
    Browse the repository at this point in the history

  5. Bump FLUX node versions after splitting out VAE encode/decode.

    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    7ebb509 View commit details
    Browse the repository at this point in the history

  6. Remove unused vae field from FLUXTextToImageInvocation.

    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    bd46666 View commit details
    Browse the repository at this point in the history

  7. Update MaskTensorToImageInvocation to support input mask tensors with… 

    … or without a channel dimension.
    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    7ad6251 View commit details
    Browse the repository at this point in the history

  8. Get a rough version of FLUX inpainting working.

    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    9a8aca6 View commit details
    Browse the repository at this point in the history

  9. Split FLUX VAE encoding out into its own node from ImageToLatentsInvo… 

    …cation.
    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    dd99ed2 View commit details
    Browse the repository at this point in the history

  10. Split FLUX VAE decoding out into its own node from LatentsToImageInvo… 

    …cation.
    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    278bba4 View commit details
    Browse the repository at this point in the history

  11. Code cleanup and documentation around FLUX inpainting.

    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    8292f6c View commit details
    Browse the repository at this point in the history

  12. Use the existence of initial latents to decide whether we are doing i… 

    …mage-to-image in the FLUX denoising node. Previously we were using the denoising_start value, but in some cases with an inpaintin mask you may want to run image-to-image from densoising_start=0.
    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    763ef06 View commit details
    Browse the repository at this point in the history

  13. Rename FluxTextToImageInvocation -> FluxDenoiseInvocation.

    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    2e092a2 View commit details
    Browse the repository at this point in the history

  14. Add denoise_end param to FluxDenoiseInvocation.

    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    2313f32 View commit details
    Browse the repository at this point in the history

  15. Rename flux_text_to_image.py -> flex_denoise.py

    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    cfdd5a1 View commit details
    Browse the repository at this point in the history

  16. Update default workflows for FLUX.

    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    fb5a24f View commit details
    Browse the repository at this point in the history

  17. Update schema.ts.

    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    23adbd4 View commit details
    Browse the repository at this point in the history

  18. Restore line that was accidentally removed during development.

    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    4255a01 View commit details
    Browse the repository at this point in the history

  19. Rename 'FLUX VAE Encode'/'FLUX VAE Decode' to 'FLUX Image to Latents'… 

    …/'FLUX Latents to Image'
    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    b43da46 View commit details
    Browse the repository at this point in the history

  20. Expose all FLUX model params in the default FLUX models.

    @RyanJDick
    RyanJDick committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    627b0bf View commit details
    Browse the repository at this point in the history