InvokeAI

mirror of https://github.com/invoke-ai/InvokeAI.git synced 2026-04-23 03:00:31 -04:00

Files

Alexander Eichhorn d8d0ebc356 Remove unused external model fields and add provider-specific parameters

- Remove negative_prompt, steps, guidance, reference_image_weights,
  reference_image_modes from external model nodes (unused by any provider)
- Remove supports_negative_prompt, supports_steps, supports_guidance
  from ExternalModelCapabilities
- Add provider_options dict to ExternalGenerationRequest for
  provider-specific parameters
- Add OpenAI-specific fields: quality, background, input_fidelity
- Add Gemini-specific fields: temperature, thinking_level
- Add new OpenAI starter models: GPT Image 1.5, GPT Image 1 Mini,
  DALL-E 3, DALL-E 2
- Fix OpenAI provider to use output_format (GPT Image) vs
  response_format (DALL-E) and send model ID in requests
- Add fixed aspect ratio sizes for OpenAI models (bucketing)
- Add ExternalProviderRateLimitError with retry logic for 429 responses
- Add provider-specific UI components in ExternalSettingsAccordion
- Simplify ParamSteps/ParamGuidance by removing dead external overrides
- Update all backend and frontend tests

2026-03-20 08:17:16 +01:00

invocations

Remove unused external model fields and add provider-specific parameters

2026-03-20 08:17:16 +01:00

routers

Remove unused external model fields and add provider-specific parameters

2026-03-20 08:17:16 +01:00

services

Remove unused external model fields and add provider-specific parameters

2026-03-20 08:17:16 +01:00

util

tests: use dangerously_run_function_in_subprocess to fix configure_torch_cuda_allocator tests