Krea

Build me a focused AI image and video generation workflow for the personal core of Krea. Requirements:

- Use Python 3.12, FastAPI, SQLite, ComfyUI as a local worker, and a small React frontend. Model original assets, edit operations, previews, and exported versions; store source IDs and timestamps for each.
- Paid product context: Manage real-time and batch generation workflows from user-owned models or APIs. Build only this DIY scope: Organize prompts and real-time or batch generation workflows, submit jobs to user-owned models or APIs, and keep outputs reproducible.
- Create prompt, negative-prompt, seed, dimensions, model, and workflow controls.
- Record exact generation parameters and workflow JSON beside every output.
- Support local image-to-image and mask inputs without uploading them elsewhere. Show estimated VRAM needs and fail clearly when a workflow or model is missing.
- Use a local web page with input, progress, review, and export views. Required input or access: GPU-capable machine or user-supplied generation API; ComfyUI. Keep credentials in .env.
- Recovery: Show estimated VRAM needs and fail clearly when a workflow or model is missing.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: An invalid input or interrupted operation must retain the source and show a recoverable state; exported records must reload with the same IDs.
- Out of scope: proprietary real-time models, GPU fleet, enhancement stack, and creative tools; frontier proprietary models. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

# AGENTS.md — Build guide for Krea

## Project scope
Organize prompts and real-time or batch generation workflows, submit jobs to user-owned models or APIs, and keep outputs reproducible.

Catalogue verdict: no. A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For Krea, manage real-time and batch generation workflows from user-owned models or APIs. The hard boundary is proprietary real-time models, gpu fleet, enhancement stack, and creative tools, plus frontier models, compute, and data.
Use the implementation prompt below to define the deliverable. Complete each phase's acceptance checks before extending the scope.

## Working agreement
- Inspect the repository and its existing instructions before choosing paths, dependencies or commands. Keep one coherent stack and explain changes to the proposed architecture.
- Plan a vertical slice that accepts a real input and produces the useful output described below. Persist only the state the prompt calls for; respect memory-only and upstream-managed workflows. Use fixtures only when they are clearly labelled.
- After scaffolding, document the actual install, development, check and build commands in README and keep them synchronized with the package or project manifest. Do not report commands as successful unless they ran.
- Work in small steps. At handoff, list implemented flows, checks actually performed, remaining blockers, and any credentials or provider setup the owner must supply.
- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.

## Prerequisites
- GPU-capable machine or user-supplied generation API
- ComfyUI
- model files with appropriate licenses
- local storage

## Stack and architecture
- Use Python 3.12, FastAPI, SQLite, ComfyUI as a local worker, and a small React frontend.
- Model original assets, edit operations, previews, and exported versions; store source IDs and timestamps for each.
- Interface for this AI image and video generation workflow: a local web page with input, progress, review, and export views.

## Security and data integrity
- Show estimated VRAM needs and fail clearly when a workflow or model is missing.
- Keep API keys and OAuth secrets in .env; redact them from logs, generated files, and error responses.
- State the practical limit: proprietary real-time models, GPU fleet, enhancement stack, and creative tools.

## Agent implementation rules
- Project rule, data: Model original assets, edit operations, previews, and exported versions; store source IDs and timestamps for each.
- Project rule, behavior: Create prompt, negative-prompt, seed, dimensions, model, and workflow controls.
- Project rule, recovery: Show estimated VRAM needs and fail clearly when a workflow or model is missing.

## Optional agent skills and references
No installable skill is listed for this guide; use the project rules and the stack documentation.

Read the linked SKILL.md and its dependencies before adding a skill. Select only the skills matching this project's runtime and task; their documentation does not supply API access, credentials or approval to perform external actions. Pin the reviewed revision where the tool supports it. Follow the chosen agent's documented project-level installation mechanism.

## Distribution ideas
These are optional planning notes. Obtain the owner's approval before publishing or contacting anyone.
- Demonstrate this AI image and video generation operation with sample or user-owned data: Create prompt, negative-prompt, seed, dimensions, model, and workflow controls.
- Show a concrete result or export: Show estimated VRAM needs and fail clearly when a workflow or model is missing.
- State the practical limit: proprietary real-time models, GPU fleet, enhancement stack, and creative tools.

## Engineering roadmap
1. Phase 1, architecture and data: Use Python 3.12, FastAPI, SQLite, ComfyUI as a local worker, and a small React frontend. Model original assets, edit operations, previews, and exported versions; store source IDs and timestamps for each.
2. Phase 2, implement: Create prompt, negative-prompt, seed, dimensions, model, and workflow controls.
3. Phase 3, implement: Record exact generation parameters and workflow JSON beside every output.
4. Phase 4, review and output: Support local image-to-image and mask inputs without uploading them elsewhere. Show estimated VRAM needs and fail clearly when a workflow or model is missing.
5. Phase 5, recovery and acceptance: Show estimated VRAM needs and fail clearly when a workflow or model is missing. Verify this invariant with a saved fixture: An invalid input or interrupted operation must retain the source and show a recoverable state; exported records must reload with the same IDs. State the practical limit: proprietary real-time models, GPU fleet, enhancement stack, and creative tools.

## Paid-product capabilities outside this build
- proprietary real-time models, GPU fleet, enhancement stack, and creative tools
- frontier proprietary models
- hosted GPU capacity
- licensed training data
- moderation and fast global delivery

## Implementation prompt
Build me a focused AI image and video generation workflow for the personal core of Krea. Requirements:

- Use Python 3.12, FastAPI, SQLite, ComfyUI as a local worker, and a small React frontend. Model original assets, edit operations, previews, and exported versions; store source IDs and timestamps for each.
- Paid product context: Manage real-time and batch generation workflows from user-owned models or APIs. Build only this DIY scope: Organize prompts and real-time or batch generation workflows, submit jobs to user-owned models or APIs, and keep outputs reproducible.
- Create prompt, negative-prompt, seed, dimensions, model, and workflow controls.
- Record exact generation parameters and workflow JSON beside every output.
- Support local image-to-image and mask inputs without uploading them elsewhere. Show estimated VRAM needs and fail clearly when a workflow or model is missing.
- Use a local web page with input, progress, review, and export views. Required input or access: GPU-capable machine or user-supplied generation API; ComfyUI. Keep credentials in .env.
- Recovery: Show estimated VRAM needs and fail clearly when a workflow or model is missing.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: An invalid input or interrupted operation must retain the source and show a recoverable state; exported records must reload with the same IDs.
- Out of scope: proprietary real-time models, GPU fleet, enhancement stack, and creative tools; frontier proprietary models. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

## Completion evidence
Demonstrate the prompt's acceptance scenarios against the scoped workflow. Include setup from a clean checkout and failure recovery. Check persistence across restart and export/restore only for the state the prompt says to store; for memory-only tools, confirm that temporary content is discarded as specified. Record actual results and remaining limitations. A detailed plan alone does not establish a working replacement.