Skip to content

docs: add image-editing example for models that accept image input - #142

Closed
kyto-agent wants to merge 1 commit into
hackclub:mainfrom
kyto-agent:image-edit-examples
Closed

kyto-agent wants to merge 1 commit into
hackclub:mainfrom
kyto-agent:image-edit-examples

Conversation

@kyto-agent

Copy link
Copy Markdown
Contributor

Image models whose architecture.input_modalities includes image (e.g. the Gemini image models) support editing an existing image by sending a base64 data URL alongside the instruction, but the model page only showed a generation example, so the edit path was undiscoverable (came up in Slack support).

This adds a dedicated "Edit an existing image" cURL example under the language tabs for such models.

Note: the pre-request cost-estimation bug that produces false 429s on large base64 images is already addressed by #135 — this PR is docs-only.

The model page shows generation examples for image models but nothing
about editing an existing image (send a base64 image alongside the
instruction), which came up in Slack support. For models whose
architecture.input_modalities includes 'image', render a dedicated
'Edit an existing image' cURL example under the language tabs.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants