[EPIC] Image generation capability: hosted API baseline plus local GPU workflows #963

Closed
opened 2026-10-27 13:38:28 +00:00 by sam · 0 comments
Owner

Goal

Add first-class image generation to Archie, with a capability surface targeting the practical baseline of the OpenAI gpt-image-2 API while also supporting image generation on a user's existing GPU.

The capability must not assume one backend. A user asking for /image is first asked which generation mechanism they prefer:

  • hosted API (starting with an OpenAI-compatible gpt-image-2 provider), or
  • local GPU generation using one of Archie's tested model/backend recipes.

Scope

  • A provider-neutral image capability contract and routing/configuration.
  • Hosted generation/editing with an OpenAI gpt-image-2-class API baseline.
  • Local GPU generation through tested, documented model/backend recipes suitable for common consumer GPUs.
  • /image clarification and execution flow across supported channels.
  • Returned image delivery, bounded inputs/outputs, errors, and tests.

Non-goals

  • Training or fine-tuning image models.
  • Bundling multi-gigabyte model weights in Archie.
  • Pretending every GPU/model combination is supported; local support must be explicit and evidence-backed.
  • Replacing the existing text-chat capability or silently selecting a paid hosted provider.

Definition of done

  • /image asks for the preferred mechanism before generation when no mechanism is already selected for the request/session.
  • Hosted generation and editing cover the documented gpt-image-2 baseline, with provider-specific differences exposed rather than hidden.
  • Local GPU generation works end-to-end with at least one tested recipe, and additional tested common models are documented with VRAM/backend requirements and runnable examples.
  • Images can be delivered through the existing channel abstractions without leaking temporary files or unbounded data.
  • Unit, integration, and failure-path tests cover routing, provider errors, clarification, local execution, and delivery.
  • Configuration, security, and operational documentation are complete.

Subtasks below are dependency-ordered where practical; each must link back to this epic and state any deliberate deviations from the hosted API baseline.

Close reason

Closed


Imported from beads archie-core-1786748942120-1-6636e629 · GitHub #496 · type epic · priority P2 · created 2026-08-14 · closed 2026-10-08

## Goal Add first-class image generation to Archie, with a capability surface targeting the practical baseline of the OpenAI `gpt-image-2` API while also supporting image generation on a user's existing GPU. The capability must not assume one backend. A user asking for `/image` is first asked which generation mechanism they prefer: - hosted API (starting with an OpenAI-compatible `gpt-image-2` provider), or - local GPU generation using one of Archie's tested model/backend recipes. ## Scope - A provider-neutral image capability contract and routing/configuration. - Hosted generation/editing with an OpenAI `gpt-image-2`-class API baseline. - Local GPU generation through tested, documented model/backend recipes suitable for common consumer GPUs. - `/image` clarification and execution flow across supported channels. - Returned image delivery, bounded inputs/outputs, errors, and tests. ## Non-goals - Training or fine-tuning image models. - Bundling multi-gigabyte model weights in Archie. - Pretending every GPU/model combination is supported; local support must be explicit and evidence-backed. - Replacing the existing text-chat capability or silently selecting a paid hosted provider. ## Definition of done - `/image` asks for the preferred mechanism before generation when no mechanism is already selected for the request/session. - Hosted generation and editing cover the documented gpt-image-2 baseline, with provider-specific differences exposed rather than hidden. - Local GPU generation works end-to-end with at least one tested recipe, and additional tested common models are documented with VRAM/backend requirements and runnable examples. - Images can be delivered through the existing channel abstractions without leaking temporary files or unbounded data. - Unit, integration, and failure-path tests cover routing, provider errors, clarification, local execution, and delivery. - Configuration, security, and operational documentation are complete. Subtasks below are dependency-ordered where practical; each must link back to this epic and state any deliberate deviations from the hosted API baseline. ### Close reason Closed --- _Imported from beads `archie-core-1786748942120-1-6636e629` · GitHub #496 · type epic · priority P2 · created 2026-08-14 · closed 2026-10-08_
sam added the mediumepic labels 2026-10-27 13:38:28 +00:00
sam self-assigned this 2026-10-27 13:38:28 +00:00
sam closed this issue 2026-10-27 13:38:28 +00:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: sam/archie#963