Support regular TextToImage

[ichernev]

It's not crystal clear from the docs, but there are two interfaces for TextToImage (ImageGeneration) models:

• one is the SDXL one, which is actually custom (i.e it might support params not available in any other model) -- shipped like this: https://deepinfra.com/docs/advanced/custom_models
• the other is shared among a few models, like:
  • https://stage.deepinfra.com/runwayml/stable-diffusion-v1-5
  • https://stage.deepinfra.com/prompthero/openjourney

Currently SDXL is very popular, so it makes sense to keep it's custom input specification intact. However, it should have a base model with Custom in the name with type-argument the concrete SDXL type (so other similar custom models can be added in the future). I'm not 100% sure how to do this in TS, but I can do some research.

And for the regular TextToImage (named ImageGeneration here) models you can have the ImageGenerationBaseModel, which has a common API across many models.

[ichernev]

The main difference between the COG-based custom models and other models, is that cog expects all the input parameters under the input key, whereas regular text-to-image expects the arguments directly in the body (like embeddings and text-generation).

[ovuruska]

Thanks for the clarifications, @ichernev. Your input has been invaluable in enhancing the functionality and usability of the package.

The improvements you've suggested, including updating the documentation, adding a base model named Custom based on the SDXL type, and conducting research on how to implement this in TypeScript, will all be incorporated in the upcoming release by this weekend.