feat: support audio-only distributed workflows (#87)

Support image, audio, or combined distributed collection with guarded audio-only worker, master, endpoint, preview, and delegate-only paths.

api/job_routes.py

@@ -295,17 +295,24 @@ async def job_complete_endpoint(request):
             errors.append("worker_id: expected non-empty string")
         if not isinstance(batch_idx, int) or batch_idx < 0:
             errors.append("batch_idx: expected non-negative integer")
-        if not isinstance(image_payload, str) or not image_payload.strip():
+        image_provided = image_payload is not None
+        audio_provided = audio_payload is not None
+        if not image_provided and not audio_provided:
+            errors.append("expected at least one of image or audio")
+        if image_provided and (not isinstance(image_payload, str) or not image_payload.strip()):
             errors.append("image: expected non-empty base64 PNG string")
-        if audio_payload is not None and not isinstance(audio_payload, dict):
+        if audio_provided and not isinstance(audio_payload, dict):
             errors.append("audio: expected object when provided")
         if not isinstance(is_last, bool):
             errors.append("is_last: expected boolean")
         if errors:
             return await handle_api_error(request, errors, 400)
 
-        tensor = _decode_canonical_png_tensor(image_payload)
-        decoded_audio = _decode_audio_payload(audio_payload) if audio_payload is not None else None
+        try:
+            tensor = _decode_canonical_png_tensor(image_payload) if image_provided else None
+            decoded_audio = _decode_audio_payload(audio_payload) if audio_provided else None
+        except ValueError as exc:
+            return await handle_api_error(request, exc, 400)
         multi_job_id = job_id.strip()
         worker_id = worker_id.strip()
 

api/orchestration/prompt_transform.py

@@ -351,16 +351,33 @@ def prune_prompt_for_worker(prompt_obj):
         downstream = _find_downstream_nodes(prompt_obj, [dist_id])
         has_removed_downstream = any(node_id != dist_id for node_id in downstream)
         if has_removed_downstream:
-            preview_id = next_id()
-            pruned_prompt[preview_id] = {
-                "inputs": {
-                    "images": [dist_id, 0],
-                },
-                "class_type": "PreviewImage",
-                "_meta": {
-                    "title": "Preview Image (auto-added)",
-                },
-            }
+            original_node = prompt_obj.get(str(dist_id), {})
+            class_type = original_node.get("class_type")
+            inputs = original_node.get("inputs", {})
+            image_connected = class_type != "DistributedCollector" or (
+                isinstance(inputs.get("images"), list)
+                and len(inputs["images"]) == 2
+            )
+            audio_connected = (
+                class_type == "DistributedCollector"
+                and isinstance(inputs.get("audio"), list)
+                and len(inputs["audio"]) == 2
+            )
+
+            if image_connected:
+                preview_id = next_id()
+                pruned_prompt[preview_id] = {
+                    "inputs": {"images": [dist_id, 0]},
+                    "class_type": "PreviewImage",
+                    "_meta": {"title": "Preview Image (auto-added)"},
+                }
+            elif audio_connected:
+                preview_id = next_id()
+                pruned_prompt[preview_id] = {
+                    "inputs": {"audio": [dist_id, 1]},
+                    "class_type": "PreviewAudio",
+                    "_meta": {"title": "Preview Audio (auto-added)"},
+                }
 
     return pruned_prompt
 
@@ -400,6 +417,10 @@ def prepare_delegate_master_prompt(prompt_obj, collector_ids):
         collector_entry = pruned_prompt.get(collector_id)
         if not collector_entry:
             continue
+        original_inputs = (prompt_obj.get(collector_id) or {}).get("inputs", {})
+        original_images = original_inputs.get("images")
+        if not (isinstance(original_images, list) and len(original_images) == 2):
+            continue
         placeholder_id = next_id()
         pruned_prompt[placeholder_id] = {
             "class_type": "DistributedEmptyImage",

nodes/collector.py

@@ -29,7 +29,6 @@ class DistributedCollectorNode:
     def INPUT_TYPES(s):
         return {
             "required": {
-                "images": ("IMAGE",),
                 "load_balance": (
                     "BOOLEAN",
                     {
@@ -38,7 +37,10 @@ class DistributedCollectorNode:
                     },
                 ),
             },
-            "optional": { "audio": ("AUDIO",) },
+            "optional": {
+                "images": ("IMAGE",),
+                "audio": ("AUDIO",),
+            },
             "hidden": {
                 "multi_job_id": ("STRING", {"default": ""}),
                 "is_worker": ("BOOLEAN", {"default": False}),
@@ -102,8 +104,9 @@ class DistributedCollectorNode:
             return None
         return {"waveform": torch.cat(waveforms, dim=-1), "sample_rate": sample_rate}
 
-    def run(self, images, load_balance=False, audio=None, multi_job_id="", is_worker=False, master_url="", enabled_worker_ids="[]", worker_batch_size=1, worker_id="", pass_through=False, delegate_only=False):
-        images = self._normalize_images_input(images)
+    def run(self, images=None, load_balance=False, audio=None, multi_job_id="", is_worker=False, master_url="", enabled_worker_ids="[]", worker_batch_size=1, worker_id="", pass_through=False, delegate_only=False):
+        if images is not None:
+            images = self._normalize_images_input(images)
         audio = self._normalize_audio_input(audio)
         load_balance = self._unwrap_list_input(load_balance)
         multi_job_id = self._unwrap_list_input(multi_job_id)
@@ -115,6 +118,14 @@ class DistributedCollectorNode:
         pass_through = self._unwrap_list_input(pass_through)
         delegate_only = self._unwrap_list_input(delegate_only)
 
+        remote_only_master = (
+            bool(multi_job_id)
+            and not is_worker
+            and (delegate_only or is_master_delegate_only())
+        )
+        if images is None and audio is None and not remote_only_master:
+            raise ValueError("DistributedCollector requires at least one image or audio input")
+
         # Create empty audio if not provided
         empty_audio = {"waveform": torch.zeros(1, 2, 1), "sample_rate": 44100}
 
@@ -141,41 +152,56 @@ class DistributedCollectorNode:
         return result
 
     async def send_batch_to_master(self, image_batch, audio, multi_job_id, master_url, worker_id):
-        """Send image batch to master via canonical JSON envelopes."""
-        batch_size = image_batch.shape[0]
-        if batch_size == 0:
-            return
-
+        """Send an image batch, optionally with audio, or an audio-only completion."""
         encoded_audio = encode_audio_payload(audio)
-
         session = await get_client_session()
         url = f"{master_url}/distributed/job_complete"
-        for batch_idx in range(batch_size):
-            img = tensor_to_pil(image_batch[batch_idx:batch_idx+1], 0)
-            byte_io = io.BytesIO()
-            img.save(byte_io, format='PNG', compress_level=0)
-            encoded_image = base64.b64encode(byte_io.getvalue()).decode('utf-8')
-            payload = {
-                "job_id": str(multi_job_id),
-                "worker_id": str(worker_id),
-                "batch_idx": int(batch_idx),
-                "image": f"data:image/png;base64,{encoded_image}",
-                "is_last": bool(batch_idx == batch_size - 1),
-            }
-            if payload["is_last"] and encoded_audio is not None:
-                payload["audio"] = encoded_audio
 
+        payloads = []
+        batch_size = 0 if image_batch is None else image_batch.shape[0]
+        if batch_size == 0:
+            if encoded_audio is None:
+                raise ValueError("Worker completion requires image or audio data")
+            payloads.append(
+                {
+                    "job_id": str(multi_job_id),
+                    "worker_id": str(worker_id),
+                    "batch_idx": 0,
+                    "audio": encoded_audio,
+                    "is_last": True,
+                }
+            )
+        else:
+            for batch_idx in range(batch_size):
+                img = tensor_to_pil(image_batch[batch_idx:batch_idx+1], 0)
+                byte_io = io.BytesIO()
+                img.save(byte_io, format='PNG', compress_level=0)
+                encoded_image = base64.b64encode(byte_io.getvalue()).decode('utf-8')
+                payload = {
+                    "job_id": str(multi_job_id),
+                    "worker_id": str(worker_id),
+                    "batch_idx": int(batch_idx),
+                    "image": f"data:image/png;base64,{encoded_image}",
+                    "is_last": bool(batch_idx == batch_size - 1),
+                }
+                if payload["is_last"] and encoded_audio is not None:
+                    payload["audio"] = encoded_audio
+                payloads.append(payload)
+
+        for payload in payloads:
+            timeout_seconds = 60 if "image" in payload else 600
             try:
                 async with session.post(
                     url,
                     json=payload,
-                    timeout=aiohttp.ClientTimeout(total=60),
+                    timeout=aiohttp.ClientTimeout(total=timeout_seconds),
                 ) as response:
                     response.raise_for_status()
             except Exception as e:
-                log(f"Worker - Failed to send canonical image envelope to master: {e}")
+                media_type = "image/audio" if "image" in payload else "audio-only"
+                log(f"Worker - Failed to send canonical {media_type} envelope to master: {e}")
                 debug_log(f"Worker - Full error details: URL={url}")
-                raise  # Re-raise to handle at caller level
+                raise
 
     def _combine_audio(self, master_audio, worker_audio, empty_audio, worker_order=None):
         """Combine audio from master and workers into a single audio output.
@@ -257,8 +283,8 @@ class DistributedCollectorNode:
         images_on_cpu,
         delegate_mode: bool,
         fallback_images,
-    ) -> torch.Tensor:
-        """Assemble final tensor: master first, then workers in enabled order."""
+    ):
+        """Assemble final tensor, or return None when the job contains only audio."""
         ordered_tensors = []
         if not delegate_mode and images_on_cpu is not None:
             for i in range(master_batch_size):
@@ -289,15 +315,15 @@ class DistributedCollectorNode:
 
         if cpu_tensors:
             return ensure_contiguous(torch.cat(cpu_tensors, dim=0))
-        elif fallback_images is not None:
+        if fallback_images is not None:
             return ensure_contiguous(fallback_images)
-        else:
-            raise ValueError("No image data collected from master or workers")
+        return None
 
     async def execute(self, images, audio, load_balance=False, multi_job_id="", is_worker=False, master_url="", enabled_worker_ids="[]", worker_batch_size=1, worker_id="", delegate_only=False):
         if is_worker:
             # Worker mode: send images and audio to master in a single batch
-            debug_log(f"Worker - Job {multi_job_id} complete. Sending {images.shape[0]} image(s) to master")
+            image_count = 0 if images is None else images.shape[0]
+            debug_log(f"Worker - Job {multi_job_id} complete. Sending {image_count} image(s) to master")
             await self.send_batch_to_master(images, audio, multi_job_id, master_url, worker_id)
             return (images, audio if audio is not None else self.EMPTY_AUDIO)
         else:
@@ -332,14 +358,15 @@ class DistributedCollectorNode:
                 master_audio = None
                 debug_log(f"Master - Job {multi_job_id}: Delegate-only mode enabled, collecting exclusively from {num_workers} workers")
             else:
-                images_on_cpu = images.cpu()
-                master_batch_size = images.shape[0]
+                if images is None:
+                    images_on_cpu = None
+                    master_batch_size = 0
+                else:
+                    images_on_cpu = ensure_contiguous(images.cpu())
+                    master_batch_size = images.shape[0]
                 master_audio = audio  # Keep master's audio for later
                 debug_log(f"Master - Job {multi_job_id}: Master has {master_batch_size} images, collecting from {num_workers} workers...")
 
-                # Ensure master images are contiguous
-                images_on_cpu = ensure_contiguous(images_on_cpu)
-
 
             # Initialize storage for collected images and audio
             worker_images = {}  # Dict to store images by worker_id and index
@@ -511,18 +538,19 @@ class DistributedCollectorNode:
                 if multi_job_id in prompt_server.distributed_pending_jobs:
                     del prompt_server.distributed_pending_jobs[multi_job_id]
 
+            combined_audio = self._combine_audio(master_audio, worker_audio, self.EMPTY_AUDIO, enabled_workers)
             try:
                 combined = self._reorder_and_combine_tensors(
                     worker_images, enabled_workers, master_batch_size, images_on_cpu, delegate_mode, images
                 )
-                debug_log(f"Master - Job {multi_job_id} complete. Combined {combined.shape[0]} images total "
-                          f"(master: {master_batch_size}, workers: {combined.shape[0] - master_batch_size})")
-
-                # Combine audio from master and workers
-                combined_audio = self._combine_audio(master_audio, worker_audio, self.EMPTY_AUDIO, enabled_workers)
+                if combined is None:
+                    debug_log(f"Master - Job {multi_job_id} complete with audio only")
+                else:
+                    debug_log(f"Master - Job {multi_job_id} complete. Combined {combined.shape[0]} images total "
+                              f"(master: {master_batch_size}, workers: {combined.shape[0] - master_batch_size})")
 
                 return (combined, combined_audio)
             except Exception as e:
                 log(f"Master - Error combining images: {e}")
-                # Return just the master images as fallback
-                return (images, audio if audio is not None else self.EMPTY_AUDIO)
+                # Preserve collected audio even when image assembly fails.
+                return (images, combined_audio)

tests/api/test_distributed_queue.py

@@ -302,6 +302,77 @@ class JobCompleteAudioPayloadTests(unittest.IsolatedAsyncioTestCase):
         self.assertEqual(queued["audio"]["sample_rate"], 44100)
         self.assertEqual(tuple(queued["audio"]["waveform"].shape), (1, 2, 4))
 
+    async def test_job_complete_accepts_audio_without_image(self):
+        queue = asyncio.Queue()
+        job_routes.prompt_server.distributed_jobs_lock = asyncio.Lock()
+        job_routes.prompt_server.distributed_pending_jobs = {"audio-only-job": queue}
+        request = _FakeRequest(
+            {
+                "job_id": "audio-only-job",
+                "worker_id": "worker-1",
+                "batch_idx": 0,
+                "audio": self._encoded_audio_payload(),
+                "is_last": True,
+            }
+        )
+
+        with patch.object(job_routes, "_decode_canonical_png_tensor") as decode_image:
+            response = await job_routes.job_complete_endpoint(request)
+
+        self.assertEqual(response.status, 200)
+        decode_image.assert_not_called()
+        queued = await queue.get()
+        self.assertIsNone(queued["tensor"])
+        self.assertEqual(queued["audio"]["sample_rate"], 44100)
+
+    async def test_job_complete_rejects_payload_without_image_or_audio(self):
+        request = _FakeRequest(
+            {
+                "job_id": "job-1",
+                "worker_id": "worker-1",
+                "batch_idx": 0,
+                "is_last": True,
+            }
+        )
+
+        response = await job_routes.job_complete_endpoint(request)
+
+        self.assertEqual(response.status, 400)
+        self.assertIn("image or audio", response.payload.get("message", "").lower())
+
+    async def test_job_complete_rejects_invalid_image_even_when_audio_is_present(self):
+        request = _FakeRequest(
+            {
+                "job_id": "job-1",
+                "worker_id": "worker-1",
+                "batch_idx": 0,
+                "image": 123,
+                "audio": self._encoded_audio_payload(),
+                "is_last": True,
+            }
+        )
+
+        response = await job_routes.job_complete_endpoint(request)
+
+        self.assertEqual(response.status, 400)
+        self.assertIn("image", response.payload.get("message", "").lower())
+
+    async def test_job_complete_returns_400_for_malformed_audio(self):
+        request = _FakeRequest(
+            {
+                "job_id": "job-1",
+                "worker_id": "worker-1",
+                "batch_idx": 0,
+                "audio": {"data": "AAAA", "shape": [1, 2], "dtype": "float32"},
+                "is_last": True,
+            }
+        )
+
+        response = await job_routes.job_complete_endpoint(request)
+
+        self.assertEqual(response.status, 400)
+        self.assertIn("audio.shape", response.payload.get("message", "").lower())
+
     def test_decode_audio_payload_rejects_bad_shape(self):
         bad = {
             "sample_rate": 44100,

tests/test_collector_list_inputs.py

@@ -124,6 +124,49 @@ def test_collector_opts_into_comfyui_list_inputs():
     assert collector.INPUT_IS_LIST is True
 
 
+def test_collector_exposes_images_as_optional_input():
+    input_types = _load_collector_module().DistributedCollectorNode.INPUT_TYPES()
+
+    assert "images" not in input_types["required"]
+    assert input_types["optional"]["images"] == ("IMAGE",)
+
+
+def test_audio_only_pass_through_returns_no_images_and_preserves_audio():
+    collector = _load_collector_module().DistributedCollectorNode()
+    audio = {"waveform": torch.ones(1, 2, 4), "sample_rate": 48000}
+
+    images, returned_audio = collector.run(images=None, audio=[audio])
+
+    assert images is None
+    assert returned_audio is audio
+
+
+def test_collector_rejects_missing_images_and_audio():
+    collector = _load_collector_module().DistributedCollectorNode()
+
+    try:
+        collector.run(images=None, audio=None)
+    except ValueError as exc:
+        assert "image or audio" in str(exc).lower()
+    else:
+        raise AssertionError("Expected collector to reject a run with no media input")
+
+
+def test_delegate_only_master_allows_no_local_media_input():
+    collector = _load_collector_module().DistributedCollectorNode()
+
+    images, audio = collector.run(
+        images=None,
+        audio=None,
+        multi_job_id=["delegate-audio-job"],
+        delegate_only=[True],
+        enabled_worker_ids=["[]"],
+    )
+
+    assert images is None
+    assert tuple(audio["waveform"].shape) == (1, 2, 1)
+
+
 def test_pass_through_collapses_comfyui_image_list_to_batch_and_unwraps_hidden_inputs():
     collector = _load_collector_module().DistributedCollectorNode()
     first = torch.zeros(1, 2, 2, 3)
@@ -203,3 +246,119 @@ def test_worker_list_input_sends_one_completion_sequence_with_last_only_on_final
     assert [payload["is_last"] for payload in posted_payloads] == [False, True]
     assert {payload["job_id"] for payload in posted_payloads} == {"job-list-1"}
     assert {payload["worker_id"] for payload in posted_payloads} == {"worker-a"}
+
+
+def test_audio_only_worker_sends_one_completion_without_image():
+    module = _load_collector_module()
+    collector = module.DistributedCollectorNode()
+    audio = {"waveform": torch.ones(1, 2, 4), "sample_rate": 48000}
+    posted = []
+
+    class _FakeResponse:
+        async def __aenter__(self):
+            return self
+
+        async def __aexit__(self, exc_type, exc, tb):
+            return False
+
+        def raise_for_status(self):
+            return None
+
+    class _FakeSession:
+        def post(self, url, json, timeout):
+            posted.append((url, json, timeout.total))
+            return _FakeResponse()
+
+    async def _fake_get_client_session():
+        return _FakeSession()
+
+    module.get_client_session = _fake_get_client_session
+    module.encode_audio_payload = lambda value: {"encoded": value is audio}
+
+    images, returned_audio = collector.run(
+        images=None,
+        audio=[audio],
+        multi_job_id=["audio-job"],
+        is_worker=[True],
+        master_url=["http://master"],
+        worker_id=["worker-a"],
+    )
+
+    assert images is None
+    assert returned_audio is audio
+    assert len(posted) == 1
+    assert posted[0][0] == "http://master/distributed/job_complete"
+    assert posted[0][2] == 600
+    assert posted[0][1] == {
+        "job_id": "audio-job",
+        "worker_id": "worker-a",
+        "batch_idx": 0,
+        "audio": {"encoded": True},
+        "is_last": True,
+    }
+
+
+def test_audio_only_master_combines_local_and_worker_audio():
+    module = _load_collector_module()
+    collector = module.DistributedCollectorNode()
+    master_audio = {"waveform": torch.ones(1, 2, 2), "sample_rate": 48000}
+    worker_audio = {"waveform": torch.full((1, 2, 3), 2.0), "sample_rate": 48000}
+    module.prompt_server.distributed_jobs_lock = asyncio.Lock()
+    queue = asyncio.Queue()
+    queue.put_nowait(
+        {
+            "worker_id": "worker-a",
+            "image_index": 0,
+            "tensor": None,
+            "audio": worker_audio,
+            "is_last": True,
+        }
+    )
+    module.prompt_server.distributed_pending_jobs = {"audio-job": queue}
+
+    images, combined_audio = asyncio.run(
+        collector.execute(
+            images=None,
+            audio=master_audio,
+            multi_job_id="audio-job",
+            enabled_worker_ids='["worker-a"]',
+        )
+    )
+
+    assert images is None
+    assert combined_audio["sample_rate"] == 48000
+    assert tuple(combined_audio["waveform"].shape) == (1, 2, 5)
+    assert torch.equal(combined_audio["waveform"][..., :2], master_audio["waveform"])
+    assert torch.equal(combined_audio["waveform"][..., 2:], worker_audio["waveform"])
+
+
+def test_delegate_only_audio_collects_worker_audio_without_placeholder_image():
+    module = _load_collector_module()
+    collector = module.DistributedCollectorNode()
+    worker_audio = {"waveform": torch.full((1, 2, 3), 2.0), "sample_rate": 48000}
+    module.prompt_server.distributed_jobs_lock = asyncio.Lock()
+    queue = asyncio.Queue()
+    queue.put_nowait(
+        {
+            "worker_id": "worker-a",
+            "image_index": 0,
+            "tensor": None,
+            "audio": worker_audio,
+            "is_last": True,
+        }
+    )
+    module.prompt_server.distributed_pending_jobs = {"delegate-audio-job": queue}
+
+    images, combined_audio = asyncio.run(
+        collector.execute(
+            images=None,
+            audio=None,
+            multi_job_id="delegate-audio-job",
+            enabled_worker_ids='["worker-a"]',
+            delegate_only=True,
+        )
+    )
+
+    assert images is None
+    assert combined_audio["sample_rate"] == 48000
+    assert torch.equal(combined_audio["waveform"], worker_audio["waveform"])

tests/test_prompt_transform.py

@@ -71,6 +71,15 @@ def _collector_only_prompt():
     }
 
 
+def _audio_only_prompt():
+    """1(Audio source) → 2(DistributedCollector) → 3(Audio sink)."""
+    return {
+        "1": {"class_type": "LoadAudio", "inputs": {}},
+        "2": {"class_type": "DistributedCollector", "inputs": {"audio": ["1", 0]}},
+        "3": {"class_type": "SaveAudio", "inputs": {"audio": ["2", 1]}},
+    }
+
+
 def _delegate_prompt():
     """1 → 2 → 3(DistributedCollector) → 4(SaveImage)"""
     return {
@@ -217,6 +226,35 @@ class PrunePromptForWorkerTests(unittest.TestCase):
         self.assertEqual(len(preview_nodes), 1)
         self.assertEqual(preview_nodes[0]["inputs"]["images"], ["4", 0])
 
+    def test_injects_preview_audio_for_audio_only_collector(self):
+        result = pt.prune_prompt_for_worker(_audio_only_prompt())
+        preview_nodes = [n for n in result.values() if n.get("class_type") == "PreviewAudio"]
+        self.assertEqual(len(preview_nodes), 1)
+        self.assertEqual(preview_nodes[0]["inputs"]["audio"], ["2", 1])
+        self.assertFalse(any(n.get("class_type") == "PreviewImage" for n in result.values()))
+
+    def test_prefers_image_preview_when_collector_has_images_and_audio(self):
+        prompt = _linear_prompt()
+        prompt["6"] = {"class_type": "LoadAudio", "inputs": {}}
+        prompt["4"]["inputs"]["audio"] = ["6", 0]
+        result = pt.prune_prompt_for_worker(prompt)
+        self.assertEqual(
+            len([n for n in result.values() if n.get("class_type") == "PreviewImage"]),
+            1,
+        )
+        self.assertFalse(any(n.get("class_type") == "PreviewAudio" for n in result.values()))
+
+    def test_preserves_image_preview_for_distributed_upscale(self):
+        prompt = {
+            "1": {"class_type": "LoadImage", "inputs": {}},
+            "2": {"class_type": "UltimateSDUpscaleDistributed", "inputs": {"upscaled_image": ["1", 0]}},
+            "3": {"class_type": "SaveImage", "inputs": {"images": ["2", 0]}},
+        }
+        result = pt.prune_prompt_for_worker(prompt)
+        preview_nodes = [n for n in result.values() if n.get("class_type") == "PreviewImage"]
+        self.assertEqual(len(preview_nodes), 1)
+        self.assertEqual(preview_nodes[0]["inputs"]["images"], ["2", 0])
+
     def test_no_preview_image_when_no_downstream(self):
         result = pt.prune_prompt_for_worker(_collector_only_prompt())
         preview_nodes = [n for n in result.values() if n.get("class_type") == "PreviewImage"]
@@ -242,7 +280,7 @@ class PrunePromptForWorkerTests(unittest.TestCase):
     def test_upscale_node_is_treated_as_distributed(self):
         prompt = {
             "1": {"class_type": "KSampler", "inputs": {}},
-            "2": {"class_type": "UltimateSDUpscaleDistributed", "inputs": {"image": ["1", 0]}},
+            "2": {"class_type": "UltimateSDUpscaleDistributed", "inputs": {"upscaled_image": ["1", 0]}},
             "3": {"class_type": "SaveImage", "inputs": {"images": ["2", 0]}},
         }
         result = pt.prune_prompt_for_worker(prompt)
@@ -285,12 +323,22 @@ class PrepareDelegateMasterPromptTests(unittest.TestCase):
         placeholder_id = empty_nodes[0][0]
         self.assertEqual(result["3"]["inputs"]["images"], [placeholder_id, 0])
 
+    def test_audio_only_collector_does_not_get_image_placeholder(self):
+        prompt = _audio_only_prompt()
+        result = pt.prepare_delegate_master_prompt(prompt, ["2"])
+        empty_nodes = [n for n in result.values() if n.get("class_type") == "DistributedEmptyImage"]
+        self.assertEqual(empty_nodes, [])
+        self.assertNotIn("images", result["2"].get("inputs", {}))
+        self.assertNotIn("audio", result["2"].get("inputs", {}))
+
     def test_one_placeholder_per_collector(self):
         """Two collectors → two placeholders."""
         prompt = {
-            "1": {"class_type": "DistributedCollector", "inputs": {}},
-            "2": {"class_type": "DistributedCollector", "inputs": {}},
+            "1": {"class_type": "DistributedCollector", "inputs": {"images": ["10", 0]}},
+            "2": {"class_type": "DistributedCollector", "inputs": {"images": ["11", 0]}},
             "3": {"class_type": "SaveImage", "inputs": {"images": ["1", 0]}},
+            "10": {"class_type": "LoadImage", "inputs": {}},
+            "11": {"class_type": "LoadImage", "inputs": {}},
         }
         result = pt.prepare_delegate_master_prompt(prompt, ["1", "2"])
         empty_nodes = [n for n in result.values() if n.get("class_type") == "DistributedEmptyImage"]