Fix PaintPlus OpenAI edit quality: edits silently fell back to dall-e-2

inpaint()/img2img()/outpaint() called /v1/images/edits without a model
field, so OpenAI defaulted every cloud edit to dall-e-2 regardless of
configuration — while txt2img used dall-e-3. Add a separate
OPENAI_EDIT_MODEL (default gpt-image-1, the only current model that
supports masked edits at ChatGPT-comparable quality), thread it through
the provider and both compose files, and handle gpt-image-1's
b64_json-only response shape alongside the url shape dall-e-2/3 return.

paintplus/docker-compose.yml

@@ -14,6 +14,8 @@ services:
       - SECRET_KEY=${SECRET_KEY:-change-this-secret-key-in-production}
       - AI_PROVIDER=${AI_PROVIDER:-mock}
       - OPENAI_API_KEY=${OPENAI_API_KEY:-}
+      - OPENAI_MODEL=${OPENAI_MODEL:-dall-e-3}
+      - OPENAI_EDIT_MODEL=${OPENAI_EDIT_MODEL:-gpt-image-1}
       - STABILITY_API_KEY=${STABILITY_API_KEY:-}
       - REPLICATE_API_KEY=${REPLICATE_API_KEY:-}
       - INVOKEAI_URL=${INVOKEAI_URL:-}