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/data_transfer_object/data_loader.py

@@ -5,7 +5,8 @@ import torch
 
 from PIL import Image
 from PIL.ImageOps import exif_transpose
-
+import av
+            
 from toolkit import image_utils
 from toolkit.basic import get_quick_signature_string
 from toolkit.dataloader_mixins import (
@@ -21,6 +22,7 @@ from toolkit.dataloader_mixins import (
     ClipImageFileItemDTOMixin,
     InpaintControlFileItemDTOMixin,
     TextEmbeddingFileItemDTOMixin,
+    AudioProcessingDTOMixin,
 )
 from toolkit.prompt_utils import PromptEmbeds, concat_prompt_embeds
 
@@ -42,6 +44,7 @@ class FileItemDTO(
     TextEmbeddingFileItemDTOMixin,
     CaptionProcessingDTOMixin,
     ImageProcessingDTOMixin,
+    AudioProcessingDTOMixin,
     ControlFileItemDTOMixin,
     InpaintControlFileItemDTOMixin,
     ClipImageFileItemDTOMixin,
@@ -55,6 +58,8 @@ class FileItemDTO(
         self.path = kwargs.get("path", "")
         self.dataset_config: "DatasetConfig" = kwargs.get("dataset_config", None)
         self.is_video = self.dataset_config.num_frames > 1 or self.dataset_config.auto_frame_count
+        self.is_audio_model = kwargs.get("is_audio_model", False)
+        self.sample_rate = kwargs.get("sample_rate", 48000)
         self.num_frames = self.dataset_config.num_frames
         self.temporal_compression = kwargs.get("temporal_compression", 8)
         size_database = kwargs.get("size_database", {})
@@ -84,8 +89,16 @@ class FileItemDTO(
                 and db_entry[2] == file_signature
             ):
                 use_db_entry = True
-
-        if use_db_entry:
+        if self.is_audio_model:
+            # get the length of the audio file in ms
+            with av.open(self.path) as c:
+                if c.duration is not None:
+                    w =  int(c.duration / 1_000)
+                else:
+                    s = c.streams.audio[0]
+                    w = int(float(s.duration * s.time_base) * 1_000)
+            h = 1
+        elif use_db_entry:
             w, h, _ = size_database[file_key]
         elif self.is_video:
             # Open the video file