fix: add FLUX VAE autoencoder for proper image decoding

Added FLUX VAE (ae.safetensors) to model configuration and updated
workflow to use it instead of non-existent pixel_space VAE.

This fixes the SaveImage data type error (1, 1, 16), |u1.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

comfyui/workflows/text-to-image/flux-dev-t2i-production-v1.json

@@ -192,8 +192,8 @@
       "properties": {
         "Node name for S&R": "VAELoader"
       },
-      "widgets_values": ["pixel_space"],
-      "title": "VAE Loader"
+      "widgets_values": ["ae.safetensors"],
+      "title": "FLUX VAE Loader"
     },
     {
       "id": 7,