Guide-yakabatana mibvunzo · Pakati Nhanho

Tsika Diffusion Multi-Concept Tuning Quiz

Ongorora Custom Diffusion's cross-attention tuning, mashoma-kupfura munhu, kugadzirisa, uye anotsigirwa nzira dzekunyora akawanda pfungwa.

Nzira dzekutungamira dzinoenderanaTsika Diffusion Multi Concept Tuning
Mubvunzo 1 ye 8

Ndeipi chikamu cheiyo diffusion modhi iyo Tsika Diffusion inonyanya kunakisa-tuni?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Ndeipi chikamu cheiyo diffusion modhi iyo Tsika Diffusion inonyanya kunakisa-tuni?
    • Makiyi uye kukosha fungidziro muchinjika-yekutarisa maseru
    • Huremu hwese muU-Net
    • Iyo VAE decoder chete
    • The text tokenizer
  2. Chii chinonzi Custom Diffusion inonyanya kukosha pakuenzaniswa nenzira imwechete-yepfungwa?
    • Kugadzira vhidhiyo pane mifananidzo
    • Kugadzira akawanda achangodzidzwa pfungwa mune chimwe chiitiko
    • Kusada mifananidzo zvachose
    • Kumhanya chete paCPUs
  3. What minimum number of training images did the Custom Diffusion paper report using in some experiments?
    • As few as four images
    • At least 500 images
    • Exactly one image in every experiment
    • The paper specifies no concept images
  4. Nei Tsika Diffusion ichishandisa seti yemifananidzo yenguva dzose kubva kune iyo pfungwa yakakura chikamu?
    • Kuti ikurumidze VAE
    • Kuti uwedzere kugadzirisa kwemifananidzo
    • Kubvisa watermarks
    • Kudzivirira overfitting uye mutauro kukukurwa pane iyo pfungwa izwi
  5. Ko maviri akadzidziswa akapatsanuka Mazano eKupatsanura anogona kushandiswa pamwechete?
    • Nekuvabatanidza kuburikidza nekumanikidzirwa optimization pamusoro pezviremera zvakatuniwa
    • Havagoni kubatanidzwa zvachose
    • Neavhareji yemifananidzo yekupinza
    • Nekudzidzirazve iyo yakazara modhi kubva pakatanga
  6. What proportion of model weights did the Custom Diffusion paper report storing for its tuned subset?
    • About 3% of the model weights
    • All model weights plus a new model copy
    • No trained parameters at all
    • A fixed 50% of the model weights
  7. Besides merging separately tuned models, how does Custom Diffusion support learning multiple concepts?
    • It requires a separate foundation model for every prompt
    • It replaces all cross-attention with a fixed lookup table
    • It can train for multiple concepts jointly
    • It can only learn one concept per model
  8. In a cross-attention layer, what do the tuned text-side key and value projections help associate?
    • Image pixels with internet search results
    • The diffusion timestep with the model's source code
    • Audio frequencies with a document's page number
    • Prompt concepts with features in the image latent representation