feat(mm): add gpt-image-2 as a starter model#9096
Open
Steve235lab wants to merge 4 commits intoinvoke-ai:mainfrom
Open
feat(mm): add gpt-image-2 as a starter model#9096Steve235lab wants to merge 4 commits intoinvoke-ai:mainfrom
Steve235lab wants to merge 4 commits intoinvoke-ai:mainfrom
Conversation
Adds OpenAI GPT-Image-2 to the external API model list. - Registers "gpt-image-2" in OpenAIProvider._GPT_IMAGE_MODELS so it uses the correct GPT Image request/response path (output_format, edits endpoint, etc.) - Adds openai_gpt_image_2 StarterModel entry with the same aspect ratios and panel schema as gpt-image-1 Notable gpt-image-2 constraints (handled by not exposing them in the panel schema): no transparent background support, input_fidelity is not configurable (always high fidelity).
gpt-image-2 is significantly slower than other GPT Image models, especially through a proxy. The default 120s timeout causes failures. Adds a per-model timeout map so other models are unaffected.
Steve235lab
requested review from
JPPhoto,
Pfannkuchensack,
blessedcoolant,
dunkeroni and
lstein
as code owners
github-actions
Bot
added
python
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
"gpt-image-2"toOpenAIProvider._GPT_IMAGE_MODELSso it uses the correct GPT Image request path (output_format, edits endpoint, etc.)openai_gpt_image_2StarterModelentry with the same aspect ratios and panel schema asgpt-image-1; reuses all existingOPENAI_GPT_IMAGE_*constants_MODEL_TIMEOUTS) with a 300 s timeout forgpt-image-2, which is significantly slower than other GPT Image models; all other models keep the existing 120 s defaultNotable gpt-image-2 constraints (intentionally not exposed in the panel schema): transparent background is not supported, and
input_fidelityis not configurable.Test plan
openai_gpt_image_2appears in the starter model list and can be installed via the Model Managergpt-image-1,gpt-image-1.5,gpt-image-1-mini) are unaffectedTested with existing test suite and manually on my self-deployed docker instance.