huggingface / huggingface/diffusers
[SD3] Incorrect stochastic sampling implementation
- Vorherrschende Sprache
- Python
- Sterne
- 34.5k
- Forks
- 7.3k
- Ø Merge
- 3 T. 3 Std.
- Gemergte PRs (30 T.)
- 91
Beschreibung
### Describe the bug
Ref to Algorithm 2 of [EDM](https://arxiv.org/abs/2206.00364), for a given sample $x_t$, noise is introduced to it reaching a higher noise level $\hat{t}$, then we evaluate network with $\hat{x_t}$, $\hat{t}$ as input. However, the current implementation evaluates network with $x_t$, $t$ as input, which is inconsistent from definition.
Current implementation is more similar with Euler-Maruyama in spirit, "One can interpret Euler–Maruyama as first adding
noise and then performing an ODE step, not from the intermediate state after noise injection, but
assuming that $x$ and $\sigma$ remained at the initial state at the beginning of the iteration step." quote from [EDM](https://arxiv.org/abs/2206.00364)
### Reproduction
no
### Logs
_No response_
### System Info
no
### Who can help?
@yiyixuxu @sayakpaul
Beitragsleitfaden
Rechercherichtung
No file, test, or entry point is named. Start by locating the stochastic sampling implementation and compare its network inputs with Algorithm 2 of the linked EDM paper, focusing on whether the noise-adjusted sample and noise level are evaluated. Done means the implementation follows that algorithm and has coverage demonstrating the corrected inputs.
Vom Indexierungsmodell aus dem Issue-Text verfasst.
Bewertung
- Tech-Stack
- python, pytorch
- Bereich
- machine-learning
- Issue-Typ
- Bug
- Schwierigkeit
- 4/5
- Geschätzter Aufwand
- 3-5 Tage
- Aktivitätsstatus
- Veraltet
- Klarheit
- Muss geklärt werden
- Anfängerfreundlichkeit
- 30/100