InvokeAI/invokeai
psychedelicious 7bc77ddb40 fix(nodes): doubly-noised latents
When using refiner with a mask (i.e. inpainting), we don't have noise provided as an input to the node.

This situation uniquely hits a code path that wasn't reviewed when gradient denoising was implemented.

That code path does two things wrong:
- It lerp'd the input latents. This was fixed in 5a1f4cb1ce.
- It added noise to the latents an extra time. This is fixed in this change.

We don't need to add noise in `latents_from_embeddings` because we do it just a lines later in `AddsMaskGuidance`.

- Remove the extraneous call to `add_noise`
- Make `seed` a required arg. We never call the function without seed anyways. If we refactor this in the future, it will be clearer that we need to look at how seed is handled.
- Move the call to create the noise to a deeper conditional, just before we call `AddsMaskGuidance`. The created noise tensor is now only used in that function, no need to create it every time.

Note: Whether or not having both noise and latents as inputs on the node is correct is a separate conversation. This change just fixes the issue with the current setup.
2024-04-11 07:21:50 -04:00
..
app fix(nodes): do not set seed on output latents from denoise latents 2024-04-11 07:21:50 -04:00
assets feat(api): chore: pydantic & fastapi upgrade 2023-10-17 14:59:25 +11:00
backend fix(nodes): doubly-noised latents 2024-04-11 07:21:50 -04:00
configs fix(mm): add missing v2-midas-inference.yaml 2024-03-27 07:48:54 -04:00
frontend fix(ui): canvas staging area & batch handling fixes 2024-04-10 21:48:34 +10:00
invocation_api Remove support for Prompt-to-Prompt cross-attention control (aka .swap()). This feature is not widely used. It does not work with SDXL and is incompatible with IP-Adapter and regional prompting. The implementation is also intertwined with both text embedding and the UNet attention layers, resulting in a high maintenance burden. For all of these reasons, we have decided to drop support. 2024-04-09 10:57:02 -04:00
version chore: v4.0.4 2024-04-06 15:15:16 +11:00
__init__.py