Refiner
って何？
https://gyazo.com/84b71b5e5e9adf1a8954fb89b96891aa
Refinement Stage Empirically, we find that the resulting model sometimes yields samples of low local quality, see Fig. 6. To improve sample quality, we train a separate LDM in the same latent space, which is specialized on high-quality, high resolution data and employ a noising-denoising process as introduced by SDEdit (28) on the samples from the base model. We follow (1) and specialize this refinement model on the first 200 (discrete) noise scales. During inference, we render latents from the base SDXL, and directly diffuse and denoise them in latent space with the refinement model (see Fig. 1), using the same text input. We note that this step is optional, but improves sample quality for detailed backgrounds and human faces, as demonstrated in Fig. 6 and Fig. 13.
refinerはモデルがどんなものでも効果があるのだろうか？
論文から察するに派生モデルを作成したらそれと同じ潜在空間でrefinerを訓練する必要がありそうだ