quiz bu lëkkale ak tegtal · Diggante Niveau
Imagen Bind-ci-Nataal Quiz
Xoolaat Imagen bind bu njëkk bi, defar cascade, threshold dinaamik, ak tànneefi dëgër ci tàggat yaram bu am dayo bu mag.
Laaj 1 de 8
In the original Imagen study's scaling comparison, which change produced larger image-quality and text-alignment gains?
Xoolaatal laaj bu nekk8 laaj
Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.
- In the original Imagen study's scaling comparison, which change produced larger image-quality and text-alignment gains?
- Discarding the language encoder entirely
- Increasing the pretrained text encoder's size rather than the diffusion model's size
- Replacing diffusion with nearest-neighbor image lookup
- Reducing every prompt to a single word
- Ban encoder text la Imagen di wéeru?
- Reelu nataal buñ jaxasoo
- LSTM bu ndaw
- Regle yuñ bind ak loxo
- ab xeetu làkk T5-XXL
- naka la ko Imagen mënee am dayo bu kawe?
- Diffusion cascade ak etape yuy yokk dayo bu mag
- Benn jéego bu mag
- Dagg ab nataal bu yaatu
- Ni ñuy boolee ñaari nataal
- What problem did original Imagen's dynamic thresholding address under strong guidance?
- A lack of text tokens in the encoder vocabulary
- The need to compress the final PNG file
- Saturation of predicted pixel values during sampling
- A missing training label for every object
- Luy banc dessin?
- Tablet de desine
- Màrku GPU
- Done yu nataali muus
- Benn référence buy wane ni ñuy jàngat xeetu bind-ci-nataal
- Lu tax ñuy tëye encodeur T5-XXL ci Imagen?
- Dafa yàqu te mënul tàggat
- Xam-xam bind bu am solo ci toxal tàggat yaram bu njëkk te amul beneen tuning
- Ngir sakkanal bayaalu disk bi kese
- Ndax bind bi amul benn njariñ
- What resolution did original Imagen's base diffusion model generate before its super-resolution stages?
- 256 by 256 pixels as the first stage
- 1024 by 1024 pixels directly
- 64 by 64 pixels
- A single pixel that was copied across the final image
- Why did the Imagen researchers add Gaussian noise to low-resolution conditioning images during super-resolution training?
- To make the upsamplers more robust to imperfect inputs from earlier stages
- To remove text conditioning from the entire cascade
- To guarantee that all training images had the same caption
- To replace the upsamplers with deterministic resizing