Add support for ACE-Step 1.5 and ACE-Step 1.5 XL. Also added dataset captioning through the UI. (#785)

* Base ace step 1.5 xl added. Generating, still wip on training and ui

* Base training code done

* Fix some issues with caching text embeddings. Update sample cards to show audio

* Fix issue with quantizing ace step

* Add album artwork to samples with waveform.

* Cleanup logs

* Add album art endpoint to speed up album art loading

* Made an make video with artwork script

* Make ui handle basic audio models. Make multi line adjustments to the editor and better syntax hilighting.

* Add prompt tagging system for special tagged models.

* prompt tagging processing for ui working.

* Moved default samples to a special file so we can add more when needed and they can be adjusted for a specific model

* Add a captioner job with music captioner that is prepped for use with the ui

* Add basit ui setup for captioning modal and handeling captioning jobs

* Starting captioning job from ui working. Still better management for it.

* Better filtering of job options in the job view for captioning jobs

* Added qwen3 vl as a captioner for images

* Have an indicator when a dataset is being captioned.

* Adjust the way caption jobs look in the queue

* Fix a few issues. Adjust defaults.

* Version bump

* Added ace step to the readme.

toolkit/config_modules.py

@@ -6,6 +6,7 @@ import random
 import torch
 import torchaudio
 
+from toolkit.audio.album_artwork import add_album_artwork
 from toolkit.prompt_utils import PromptEmbeds
 from torchao.quantization.quant_primitives import _DTYPE_TO_BIT_WIDTH
 
@@ -1201,13 +1202,16 @@ class GenerateImageConfig:
                 raise ValueError(f"Unsupported video format {self.output_ext}")
         elif self.output_ext in ['wav', 'mp3']:
             # save audio file
+            audio_path = self.get_image_path(count, max_count)
             torchaudio.save(
-                self.get_image_path(count, max_count), 
+                audio_path, 
                 image[0].to('cpu'),
                 sample_rate=48000, 
                 format=None, 
                 backend=None
             )
+            if self.output_ext == 'mp3':
+                add_album_artwork(audio_path)
         else:
             # TODO save image gen header info for A1111 and us, our seeds probably wont match
             image.save(self.get_image_path(count, max_count))