[diffusion] refactor: gate fast vae paths by quality (#33849)

This commit is contained in:
Mick
2026-08-07 12:39:55 +08:00
committed by GitHub
parent 914644e81c
commit c2657cc4bf
10 changed files with 105 additions and 37 deletions
@@ -70,6 +70,10 @@ The server implements an OpenAI-compatible Images API under the `/v1/images` nam
**Endpoint:** `POST /v1/images/generations`
#### Request quality
`quality` selects a model-owned sampling level when that model advertises one: use `lossless` for the reference path or `high` for a validated accelerated path. Omit it (or send OpenAI's default `auto`) to keep the runtime default. It is distinct from `output_quality`, which controls only output-file compression. The same extension is accepted by image edits and video requests.
**Python Example (b64_json response):**
```python Python