smart_image_gen v0.7.7: enforce style inheritance for edit_image

Vision-capable LLMs misclassify rendered subjects when picking a
style — observed: model called juggernaut for an edit on a furry-il
generation because the rendered character looked 'photoreal-ish' to
its vision encoder. Each visual judgment is independent so styles
flip mid-chat.

Flipped resolution order in edit_image so inheritance from the prior
generate_image / edit_image call DOMINATES the LLM's explicit style
arg. The LLM's choice only wins when there's nothing to inherit
(first edit in a chat, fresh user upload). Workaround for legitimate
style changes is starting a new chat.

System prompt updated to match: tells the LLM that style inheritance
is enforced, that passing style on follow-up calls is ignored, and
that user requests for style change require a new chat.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
57_WolveandClaude Opus 4.7 committed 2026-04-19 17:53:32 -05:00
1 parent 20d4bd5b72
commit ec6108888a
3 files changed
+31 -25

No files matched your search

@@ -87,18 +87,20 @@ STYLES (pick one):
furry-il anthropomorphic, Illustrious base (default for any
furry/anthro request)
STYLE FOR edit_image — pick in this order:
STYLE FOR edit_image — the tool ENFORCES inheritance: once a style
has been used in this chat, every subsequent edit_image call uses
the same style regardless of what you pass. Behaviour:
- The image was generated by you earlier in this chat → omit `style`,
the tool auto-inherits from the previous call.
- The user just UPLOADED an image → look at it and pick the style
that matches what you see (anthropomorphic furry/scaly/feathered
character → furry-il, pony score-tag art → pony, photo / portrait
→ photo or juggernaut, anime → pony, ambiguous → general). Keep
using that style for subsequent edits in the same chat.
- Always pick for the DESIRED OUTPUT, but for normal edits the
desired output IS the input style — only override when the user
explicitly wants a style change ("turn this anime into a photo").
- Edit on an image generated earlier in this chat → OMIT `style`
entirely. The tool will use the established style. Passing it is
harmless but ignored.
- Edit on a fresh user upload (no prior tool call in chat) → look at
the image and pick a style: anthropomorphic furry/scaly/feathered
→ furry-il; pony score-tag art → pony; photo / portrait → photo
or juggernaut; anime → pony; ambiguous → general.
- Style cannot be changed mid-chat. If the user wants a different
style, tell them they need to start a new chat — the tool ignores
style overrides on follow-up calls.
edit_image has TWO MODES — pick based on whether the change is local
or global: