Quiz collegato alla guida · Medio Livello
Quiz sulla distillazione a diffusione contraddittoria e sui modelli turbo
Verifica come le perdite di distillazione del contraddittorio e dell'insegnante si combinano nell'ADD, come differisce il LADD e cosa rinunciano i modelli turbo in termini di diversità e controllo.
Domanda 1 di 8
Quali due perdite combina ADD?
Anteprima di ogni domanda8 domande
Le risposte e le spiegazioni vengono visualizzate mentre rispondi al quiz.
- Quali due perdite combina ADD?
- An FID loss and a CLIP loss
- An adversarial loss and a distillation loss from a teacher
- A perceptual loss and a pixel loss only
- A contrastive loss and cross-entropy
- Quale modello è stato rilasciato insieme al paper ADD?
- Flux.1 dev
- DALL-E 3
- SDXL Turbo
- Diffusione stabile 1.5
- Quale backbone utilizza il discriminatore di ADD?
- A frozen DINOv2 feature network with trainable heads
- A fully trainable Inception network
- The teacher's text encoder
- No backbone; it compares raw pixels
- In che modo LADD differisce da ADD?
- It uses more denoising steps
- It removes the teacher
- It only works for video
- It runs the discriminator in latent space using the teacher's features
- Perché i prompt negativi hanno spesso poco effetto sui modelli turbo?
- The tokenizer filters them out
- The models have no text encoder
- Classifier-free guidance is typically built in during distillation
- Negative prompts only work at 1024x1024
- What happens if you run a normal, undistilled diffusion model at one step?
- It matches SDXL Turbo
- It usually produces a blurry, unfinished image
- It generates video
- It refuses to run
- Which quality trade-off is common in distilled few-step models?
- Higher diversity than the teacher
- Better text rendering in every case
- Support for unlimited resolution
- Less variety across different seeds
- In ADD's distillation loss, what is the student's target?
- The teacher's denoised prediction of the re-noised student output
- A random real image
- The discriminator's logits
- The CLIP score of the prompt