GitLab

support masked attention.

This node lets you generate a batch of images with different elevations or
azimuths by setting the elevation_batch_increment and/or
azimuth_batch_increment.

It also sets the batch index for the latents so that the same init noise is
used on each frame.

A POST request to /free with: {"unload_models":true}
will unload models from vram.

A POST request to /free with: {"free_memory":true}
will unload models and free all cached data from the last run workflow.

This is an old model.

Load the checkpoint like a regular one and use the new
SD_4XUpscale_Conditioning node.

Replace constants with downscale_ratio and latent_channels.

Allow VALIDATE_INPUTS to only validate specific inputs.

* Add `title` to the API workflow json.

* API: Move `title` to `_meta` dictionary, imply unused.

Let me know if this breaks anything.

Update from upstream repo.

Auto select value in prompt.

Increase maximum number of nodes to 10k.