Create README.md

README.md

@@ -0,0 +1,128 @@
+---
+language:
+  - en
+license: other
+pipeline_tag: text-to-image
+tags:
+  - midjourney
+  - text-to-image
+  - image-to-image
+inference: false
+---
+
+# Midjourney API
+
+Community model card for calling Midjourney through a REST API.
+
+Midjourney has no official public API. This repo documents the `midjourney` model as exposed by [Apiframe](https://apiframe.ai/docs/images/midjourney): text-to-image on V8.2, a 4-image grid per job, and follow-up actions (upsample, variation, inpaint, outpaint, pan). Image-to-video is a separate model id, `midjourney-video`.
+
+This repository does not host weights. Midjourney is a closed model. Inference runs remotely.
+
+<img src="https://apiframe.ai/models-examples/midjourney-glitter-beauty-macro-neon-lashes-feather.webp" alt="Sample output" width="280" />
+
+## Model description
+
+| | |
+|---|---|
+| Architecture | Midjourney V8.2 (current default) |
+| Task | text-to-image; image-to-image via follow-up actions |
+| Output | 4 images + `gridUrl` |
+| Aspect ratios | `1:1`, `3:4`, `4:3`, `9:16`, `16:9`, `21:9` |
+| Typical latency | ~50s |
+
+## How to use
+
+```bash
+pip install requests
+```
+
+```python
+import os
+import time
+import requests
+
+API = "https://api.apiframe.ai/v2"
+headers = {
+    "X-API-Key": os.environ["APIFRAME_API_KEY"],
+    "Content-Type": "application/json",
+}
+
+job = requests.post(
+    f"{API}/images/generate",
+    headers=headers,
+    json={
+        "model": "midjourney",
+        "prompt": "editorial still life of a red heirloom tomato and mimosa, cobalt background",
+        "midjourneyParams": {"aspect_ratio": "16:9"},
+    },
+).json()
+
+while True:
+    result = requests.get(f"{API}/jobs/{job['jobId']}", headers=headers).json()
+    if result["status"] in ("COMPLETED", "FAILED"):
+        break
+    time.sleep(2)
+
+print(result.get("result"))
+```
+
+`result["images"]` is a list of 4 CDN URLs. Pass `webhookUrl` on the generate call if you do not want to poll.
+
+### Follow-up actions
+
+```python
+import os
+import requests
+
+headers = {
+    "X-API-Key": os.environ["APIFRAME_API_KEY"],
+    "Content-Type": "application/json",
+}
+
+requests.post(
+    "https://api.apiframe.ai/v2/images/midjourney/action",
+    headers=headers,
+    json={
+        "parentJobId": "JOB_ID",
+        "action": "upsample",  # variation | inpaint | outpaint | pan
+        "index": 1,            # 1-4
+    },
+)
+```
+
+### Image-to-video
+
+```python
+import os
+import requests
+
+headers = {
+    "X-API-Key": os.environ["APIFRAME_API_KEY"],
+    "Content-Type": "application/json",
+}
+
+requests.post(
+    "https://api.apiframe.ai/v2/videos/generate",
+    headers=headers,
+    json={
+        "model": "midjourney-video",
+        "prompt": "slow push in, soft daylight",
+        "midjourneyVideoParams": {
+            "start_image": "https://example.com/still.jpg",
+            "motion": "low",
+            "resolution": "hd",
+        },
+    },
+)
+```
+
+## Limitations
+
+- Closed model. No weights, fine-tuning, or local inference.
+- Not an official Midjourney endpoint. Requires an Apiframe API key (`X-API-Key`).
+- Commercial use follows [Midjourney's terms](https://docs.midjourney.com/hc/en-us/articles/32080852940557-Community-Guidelines).
+- Generated media is retained on the CDN for 90 days.
+
+## License
+
+Outputs are subject to Midjourney's terms. This card is documentation only. Apiframe is not affiliated with, endorsed by, or sponsored by Midjourney, Inc.