fix(image_gen): disable default-on upscaling — opt-in only - #87883
Merged
Conversation
The Aug 8 default-on upscaling policy (66ea4e6) chained the Clarity Upscaler after every sub-2MP generation. Clarity is an SD1.5 creative tile-diffusion enhancer (creativity 0.35, "masterpiece" prompt prefix) — it redraws content, which degraded output on 100% of generations for models like GPT Image 2 and Ideogram whose value is precise text rendering, CJK, and photorealistic detail. Policy now: no model upscales by default, on FAL or Krea. The `upscale` tool param remains as a per-call opt-in (`upscale: true`); explicit requests still chain Clarity (FAL) / Krea Enhance as before. - FAL catalog: all 17 default-on entries flipped to upscale=False - Krea plugin: medium + medium-turbo per-model defaults flipped off - Tool schema: upscale param described as opt-in with a fidelity warning - Tests updated: catalog invariant now pins all-off; default-on cases now assert no upscaler call - Docs (en + zh) updated to the opt-in policy
Contributor
૮ >ﻌ< ა ci reviewran on 871024f — fix(image_gen): disable default-on upscaling everywhere — op
|
alt-glitch
added
type/bug
This was referenced Aug 19, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Upscaling no longer runs by default on any image model — it is strictly per-call opt-in (
upscale: true).Root cause of the quality regression: 66ea4e6 (Aug 8) flipped
upscale: Trueon every sub-2MP FAL/Krea model, chaining the Clarity Upscaler — an SD1.5 creative tile-diffusion enhancer (creativity 0.35, "masterpiece" prompt prefix) that redraws content — after 100% of generations. For models whose value is precise output (GPT Image 2 text/CJK rendering, Ideogram typography, photorealistic faces), every image came out visibly degraded.Changes
tools/image_generation_tool.py: all 17 default-on FAL catalog entries →upscale: False; tool-schema description now documents opt-in + fidelity caveatplugins/image_gen/krea/__init__.py: medium + medium-turbo per-model defaults → offtests/tools/test_image_generation.py: catalog invariant now pins all-off; default-path cases assert no upscaler calltests/plugins/image_gen/test_krea_provider.py: default-on cases updated to offwebsite/docs(en + zh): upscaling section rewritten to the opt-in policyValidation
upscaled: false, raw model output returnedExplicit
upscale: truestill chains Clarity (FAL) / Krea Enhance exactly as before.Infographic