Kevin Turner
Kevin Turner
Textual Inversion, concept embeddings, whatever we're calling it: that thing where a prompt can include some tokens that aren't included in the base model, and we load the vectors for...
Model loading is significantly different with diffusers, and I'm not sure how best to integrate it with the existing ModelCache: https://github.com/invoke-ai/InvokeAI/blob/c607d4fe6ccb0f13056d5fee5346989255fe3ccd/ldm/invoke/model_cache.py#L29-L37 diffusers takes advantage of [🤗accelerate] by default. I don't...
The inpainting docs make a big point of the importance of retaining the color values of transparent pixels: https://invoke-ai.github.io/InvokeAI/features/INPAINTING/ but the way things are now (2.2.3), any transparency in the...
If you manage to trigger some exception from the `invoke>` prompt, it currently prints the traceback and crashes the whole process. It should act more like ipython does, where it...
The diffusers implementation used by #1583 will automatically use xformers by default, ***if*** it is installed. However, xformers is not pip-installable, so it will be a non-trivial task for our...
> _write config first and then download everything in config,_ > _or download first and write config for downloads?_ The diffusers API is happy to load model weights on demand...
Invoke has a threshold feature that currently applies only to k-diffusion samplers. This should be generalized to apply to all samplers and thus also for #1583. Documentation of the feature:...
### Describe the bug The model hub seems to be having a bad time at the moment. That's a bummer, but I expect my application should still work fine in...
Model Manager UI needs some changes to support diffusers models: - **Description:** this stays the same! - **~Config~:** remove; a model's config file is always in a standard location in...
We generate a lot of images. I would like them to be encoded more efficiently. I don't need the encoding to be lossless. I often convert the images I've generated...