fix(vae): honor an explicitly requested taesd variant

get_model discarded the variant its caller asked for and re-derived one from
the loaded model type. None of the video model types appear in those sets, so
every video caller got None back and no tiny decoder at all, while kandinsky5
matched the flux group and would have been handed an image decoder.

The derivation now runs only when the caller named nothing. Callers that name
nothing are unaffected, and the one video type that resolved before keeps the
same variant and cache key.

modules/vae/sd_vae_taesd.py

@@ -58,8 +58,8 @@ def warn_once(msg, variant=None):
 
 
 def get_model(model_cls, variant=None):
-    if variant is not None:
-        pass
+    if variant is not None: # the caller named the variant it wants; the ladder below only derives one
+        return model_cls, variant
     if model_cls in {'sd'}:
         model_cls = 'sd'
         variant = shared.opts.taesd_variant