Commit History

  1. Model card: give the table real headers

    Verified signature
    31b30ef

  1. Shape folders: metadata, slot layout, tokenizer, autoencoders per shape (imagine 0.12)

    Verified signature
    726bf54
  2. Shape folders: metadata, slot layout, tokenizer, autoencoders per shape (imagine 0.12)

    Verified signature
    799d418
  3. Shape folders: metadata, slot layout, tokenizer, autoencoders per shape (imagine 0.12)

    Verified signature
    0bff881
  4. Shape folders: metadata, slot layout, tokenizer, autoencoders per shape (imagine 0.12)

    Verified signature
    9bec99f
  5. 4:3 edit transformer with the LoRA slot

    Verified signature
    e34f06a
  6. 4:3 t2i transformer with the LoRA slot

    Verified signature
    90f7090
  7. 2x3 edit transformer with the LoRA slot

    Verified signature
    eba84e2
  8. 3x2 edit transformer with the LoRA slot

    Verified signature
    05b7d23
  9. 3x4 edit transformer with the LoRA slot

    Verified signature
    21de675
  10. 9x16 edit transformer with the LoRA slot

    Verified signature
    eebc4e2
  11. 16x9 edit transformer with the LoRA slot

    Verified signature
    d9fd3fd
  12. 3x2 t2i transformer with the LoRA slot

    Verified signature
    d4eed44
  13. 4x5 t2i transformer with the LoRA slot

    Verified signature
    59f7447
  14. 9x16 t2i transformer with the LoRA slot

    Verified signature
    d6f91f8
  15. 16:9 text-to-image transformer with the LoRA slot (bit-identical to aspect-16x9's without a person)

    Verified signature
    17611f7
  16. 1:1 editing transformer with the LoRA slot (bit-identical to the plain one without a person)

    Verified signature
    2a85434
  17. Name the LoRA-slot transformer TransformerSlot.aimodel (imagine 0.11.0): a binary from before the slot finds no Transformer.aimodel and fetches the plain one from its own pinned commit instead of failing on the slot's inputs

    Verified signature
    7e7e4ba
  18. Transformer.aimodel is now the LoRA-slot export (rank 16): zero LoRA inputs = the plain transformer bit for bit; slot.json names the layers⁠

    Verified signature
    b33b6f8
  19. lora-slot-r16: FLUX.2 Klein 4B transformer with LoRA matrices as inputs (rank 16)

    Verified signature
    cc92846

  1. Model card: 9:16 and 4:5 shapes

    Verified signature
    144dfad
  2. Add 4:5 (896 × 1120): transformer + decoder for this shape; shares ../TextEncoder.aimodel

    Verified signature
    3703dc6
  3. Add 9:16 (768 × 1344): transformer + decoder for this shape; shares ../TextEncoder.aimodel

    Verified signature
    be1c934

  1. 16:9 (1344 x 768) export in aspect-16x9/, and the card says how shapes cost

    Verified signature
    4fd1cb3
  2. Core AI conversion, model card, licences and NOTICE

    Verified signature
    aae9a84
  3. initial commit

    Verified signature
    e8ab1a9