Fan-out workflow: describe + extract JSON details in parallel, chain into story writer

run.py

@@ -1,4 +1,5 @@
 import base64
+import json
 import mimetypes
 import os
 
@@ -6,6 +7,8 @@ import gradio as gr
 from huggingface_hub import get_token
 from openai import OpenAI
 
+MODEL = "deepseek-ai/DeepSeek-V4.1-Flash:novita"
+
 
 def _to_data_url(image) -> str:
     """Workflow image ports arrive as FileData-like dicts, e.g.
@@ -29,32 +32,21 @@ def _to_data_url(image) -> str:
     raise ValueError(f"Unsupported image value: {str(image)[:200]}")
 
 
-def describe_image(
-    image: dict, prompt: str, token: gr.OAuthToken | None = None
-) -> str:
-    """Describe an uploaded image with DeepSeek-V4.1-Flash.
+def _chat(content: list, token: "gr.OAuthToken | None", json_mode: bool = False) -> str:
+    """One chat completion against DeepSeek-V4.1-Flash via the HF router.
 
-    The `token` parameter is injected by gr.Workflow per request: on Spaces it
-    is the visitor's OAuth token; locally it falls back to the host's
+    `token` is injected by gr.Workflow per request: on Spaces it is the
+    visitor's OAuth token; locally it falls back to the host's
     `huggingface_hub login` token. It never appears as a canvas port.
     """
     api_key = token.token if token else get_token()
-    client = OpenAI(
-        base_url="https://router.huggingface.co/v1",
-        api_key=api_key,
-    )
+    client = OpenAI(base_url="https://router.huggingface.co/v1", api_key=api_key)
+    kwargs = {"response_format": {"type": "json_object"}} if json_mode else {}
     stream = client.chat.completions.create(
-        model="deepseek-ai/DeepSeek-V4.1-Flash:novita",
-        messages=[
-            {
-                "role": "user",
-                "content": [
-                    {"type": "text", "text": prompt},
-                    {"type": "image_url", "image_url": {"url": _to_data_url(image)}},
-                ],
-            }
-        ],
+        model=MODEL,
+        messages=[{"role": "user", "content": content}],
         stream=True,
+        **kwargs,
     )
     output = ""
     for chunk in stream:
@@ -63,7 +55,61 @@ def describe_image(
     return output
 
 
+def describe_image(
+    image: dict, prompt: str, token: gr.OAuthToken | None = None
+) -> str:
+    """Describe an uploaded image with DeepSeek-V4.1-Flash."""
+    return _chat(
+        [
+            {"type": "text", "text": prompt},
+            {"type": "image_url", "image_url": {"url": _to_data_url(image)}},
+        ],
+        token,
+    )
+
+
+def extract_details(image: dict, token: gr.OAuthToken | None = None) -> dict:
+    """Extract structured details from the image as JSON."""
+    text = _chat(
+        [
+            {
+                "type": "text",
+                "text": (
+                    "Analyze this image and respond with a JSON object with keys: "
+                    '"subject" (main subject), "setting" (where it is), '
+                    '"colors" (list of dominant colors), "mood" (one word), '
+                    '"objects" (list of notable objects).'
+                ),
+            },
+            {"type": "image_url", "image_url": {"url": _to_data_url(image)}},
+        ],
+        token,
+        json_mode=True,
+    )
+    return json.loads(text)
+
+
+def write_story(description: str, token: gr.OAuthToken | None = None) -> str:
+    """Write a short story based on an image description."""
+    return _chat(
+        [
+            {
+                "type": "text",
+                "text": (
+                    "Write a short, vivid 3-sentence story inspired by this "
+                    f"image description:\n\n{description}"
+                ),
+            }
+        ],
+        token,
+    )
+
+
 gr.Workflow(
-    bind={"Describe Image": describe_image},
+    bind={
+        "Describe Image": describe_image,
+        "Extract Details": extract_details,
+        "Write Story": write_story,
+    },
     graph="workflow.json",
 ).launch()

workflow.json

@@ -1,50 +1,30 @@
 {
   "schema_version": "2",
-  "name": "DeepSeek Image Describer",
+  "name": "DeepSeek Image Studio",
   "references": [
     {
       "id": "ref_image",
       "label": "Upload Image",
       "role": "reference",
       "asset_type": "image",
-      "inputs": [
-        {
-          "id": "in",
-          "label": "Image",
-          "type": "image"
-        }
-      ],
-      "outputs": [
-        {
-          "id": "out",
-          "label": "Image",
-          "type": "image"
-        }
-      ],
-      "data": {},
-      "width": 260
+      "x": 40,
+      "y": 180,
+      "width": 260,
+      "inputs": [{"id": "in", "label": "Image", "type": "image"}],
+      "outputs": [{"id": "out", "label": "Image", "type": "image"}],
+      "data": {}
     },
     {
       "id": "ref_prompt",
       "label": "Prompt",
       "role": "reference",
       "asset_type": "text",
-      "inputs": [
-        {
-          "id": "in",
-          "label": "Text",
-          "type": "text"
-        }
-      ],
-      "outputs": [
-        {
-          "id": "out",
-          "label": "Text",
-          "type": "text"
-        }
-      ],
-      "data": {},
-      "width": 260
+      "x": 40,
+      "y": 520,
+      "width": 260,
+      "inputs": [{"id": "in", "label": "Text", "type": "text"}],
+      "outputs": [{"id": "out", "label": "Text", "type": "text"}],
+      "data": {"out": "Describe this image in one sentence."}
     }
   ],
   "operators": [
@@ -54,30 +34,45 @@
       "role": "operator",
       "kind": "fn",
       "fn": "Describe Image",
+      "x": 460,
+      "y": 80,
+      "width": 300,
       "inputs": [
-        {
-          "id": "in_image",
-          "label": "image",
-          "type": "image",
-          "required": true
-        },
-        {
-          "id": "in_prompt",
-          "label": "prompt",
-          "type": "text",
-          "required": true
-        }
+        {"id": "in_image", "label": "image", "type": "image", "required": true},
+        {"id": "in_prompt", "label": "prompt", "type": "text", "required": true}
       ],
-      "outputs": [
-        {
-          "id": "out_0",
-          "label": "output",
-          "type": "text",
-          "output_index": 0
-        }
+      "outputs": [{"id": "out_0", "label": "output", "type": "text", "output_index": 0}],
+      "data": {}
+    },
+    {
+      "id": "op_extract",
+      "label": "Extract Details",
+      "role": "operator",
+      "kind": "fn",
+      "fn": "Extract Details",
+      "x": 460,
+      "y": 420,
+      "width": 300,
+      "inputs": [
+        {"id": "in_image", "label": "image", "type": "image", "required": true}
       ],
-      "data": {},
-      "width": 300
+      "outputs": [{"id": "out_0", "label": "output", "type": "json", "output_index": 0}],
+      "data": {}
+    },
+    {
+      "id": "op_story",
+      "label": "Write Story",
+      "role": "operator",
+      "kind": "fn",
+      "fn": "Write Story",
+      "x": 920,
+      "y": 80,
+      "width": 300,
+      "inputs": [
+        {"id": "in_description", "label": "description", "type": "text", "required": true}
+      ],
+      "outputs": [{"id": "out_0", "label": "output", "type": "text", "output_index": 0}],
+      "data": {}
     }
   ],
   "subjects": [
@@ -86,48 +81,80 @@
       "label": "Description",
       "role": "subject",
       "asset_type": "text",
-      "inputs": [
-        {
-          "id": "in",
-          "label": "Text",
-          "type": "text"
-        }
-      ],
-      "outputs": [
-        {
-          "id": "out",
-          "label": "Text",
-          "type": "text"
-        }
-      ],
-      "data": {},
-      "width": 320
+      "x": 1380,
+      "y": 40,
+      "width": 320,
+      "inputs": [{"id": "in", "label": "Text", "type": "text"}],
+      "outputs": [{"id": "out", "label": "Text", "type": "text"}],
+      "data": {}
+    },
+    {
+      "id": "sub_details",
+      "label": "Details",
+      "role": "subject",
+      "asset_type": "json",
+      "x": 920,
+      "y": 420,
+      "width": 320,
+      "inputs": [{"id": "in", "label": "JSON", "type": "json"}],
+      "outputs": [{"id": "out", "label": "JSON", "type": "json"}],
+      "data": {}
+    },
+    {
+      "id": "sub_story",
+      "label": "Story",
+      "role": "subject",
+      "asset_type": "text",
+      "x": 1380,
+      "y": 300,
+      "width": 320,
+      "inputs": [{"id": "in", "label": "Text", "type": "text"}],
+      "outputs": [{"id": "out", "label": "Text", "type": "text"}],
+      "data": {}
     }
   ],
   "edges": [
     {
       "id": "e1",
-      "from_node_id": "ref_image",
-      "from_port_id": "out",
-      "to_node_id": "op_describe",
-      "to_port_id": "in_image",
+      "from_node_id": "ref_image", "from_port_id": "out",
+      "to_node_id": "op_describe", "to_port_id": "in_image",
       "type": "image"
     },
     {
       "id": "e2",
-      "from_node_id": "ref_prompt",
-      "from_port_id": "out",
-      "to_node_id": "op_describe",
-      "to_port_id": "in_prompt",
+      "from_node_id": "ref_prompt", "from_port_id": "out",
+      "to_node_id": "op_describe", "to_port_id": "in_prompt",
       "type": "text"
     },
     {
       "id": "e3",
-      "from_node_id": "op_describe",
-      "from_port_id": "out_0",
-      "to_node_id": "sub_description",
-      "to_port_id": "in",
+      "from_node_id": "ref_image", "from_port_id": "out",
+      "to_node_id": "op_extract", "to_port_id": "in_image",
+      "type": "image"
+    },
+    {
+      "id": "e4",
+      "from_node_id": "op_describe", "from_port_id": "out_0",
+      "to_node_id": "op_story", "to_port_id": "in_description",
+      "type": "text"
+    },
+    {
+      "id": "e5",
+      "from_node_id": "op_describe", "from_port_id": "out_0",
+      "to_node_id": "sub_description", "to_port_id": "in",
+      "type": "text"
+    },
+    {
+      "id": "e6",
+      "from_node_id": "op_extract", "from_port_id": "out_0",
+      "to_node_id": "sub_details", "to_port_id": "in",
+      "type": "json"
+    },
+    {
+      "id": "e7",
+      "from_node_id": "op_story", "from_port_id": "out_0",
+      "to_node_id": "sub_story", "to_port_id": "in",
       "type": "text"
     }
   ]
-}
+}