Hugging Face's logo

Spaces:
dagloop5
/
TestingRef2va
Running on Zero

App Files Community
TestingRef2va

Commit History

  1. Mirror the conditioner's 16-canvas table (fast 4:3, 3:4 and 21:9 added)

    multimodalart HF Staff
    Verified signature
    2225cd2

  2. Point at the public multimodalart/qwen3vl-conditioner, called without a token

    multimodalart HF Staff
    Verified signature
    63f7c91

  3. Point at the public multimodalart/qwen3vl-conditioner, called without a token

    multimodalart HF Staff
    Verified signature
    1f02c70

  4. Fast canvas stays the default; the examples carry full-resolution canvases

    multimodalart HF Staff
    Verified signature
    1aa28b5

  5. Full 16:9 as the default canvas; match the conditioner's renamed fast label

    multimodalart HF Staff
    Verified signature
    6237c6a

  6. Upload subject.png

    multimodalart HF Staff
    Verified signature
    44f6712

  7. A real person as the subject reference (Pexels, Oliver Dohrn)

    multimodalart HF Staff
    Verified signature
    691e8f4

  8. A real person as the subject reference (Pexels, Oliver Dohrn)

    multimodalart HF Staff
    Verified signature
    08f770f

  9. Real speech for the audio example: LibriSpeech dev-clean 1462-170145-0022

    multimodalart HF Staff
    Verified signature
    b4c6b95

  10. Real speech for the audio example: LibriSpeech dev-clean 1462-170145-0022

    multimodalart HF Staff
    Verified signature
    a42dbb8

  11. A real subject for the reference example

    multimodalart HF Staff
    Verified signature
    d04b4d3

  12. Dynamic GPU duration from the packed sequence, cached examples, torchaudio note

    multimodalart HF Staff
    Verified signature
    f03920f

  13. torchaudio for off-rate reference soundtracks; title, fillable width, slot height

    multimodalart HF Staff
    Verified signature
    ced31c4

  14. torchaudio for off-rate reference soundtracks; title, fillable width, slot height

    multimodalart HF Staff
    Verified signature
    4bdd7d9

  15. Rename to MiniMax-H3 Reference; describe the tab order and image slots

    multimodalart HF Staff
    Verified signature
    06e2317

  16. Images/audio/video tab order, expandable image slots, native attention for the VAEs

    multimodalart HF Staff
    Verified signature
    79e1481

  17. Mirror the generator's title, theme and advanced-options layout

    multimodalart HF Staff
    Verified signature
    cf77190

  18. Describe the reference tabs

    multimodalart HF Staff
    Verified signature
    fc319a7

  19. One tab per reference modality, in reading order

    multimodalart HF Staff
    Verified signature
    508462c

  20. MiniMax-H3 ref2va, the denoising half of the split deployment

    multimodalart HF Staff
    Verified signature
    9e3b8ca

  21. initial commit

    multimodalart HF Staff
    Verified signature
    7809b26