• Added support for image_as_end_frame for Gen-3 Alpha Turbo
• Updated article Discord CDN Proxy

We added support for Gen-3 Alpha Extend

We pushed a small update today with the following changes:
• The InsightFaceSwap API will now return 429 instead of 400 when the InsightFaceSwap Bot reports "...there are XX commands in the free-plan job queue, please wait and do not re-submit". This change will allow API consumers to apply the same 429: Too Many Requests logic to wait and resubmit.
• All APIs for Discord bots will now return 400 with the error message: "Discord token for channel <channel_id> has expired or is invalid. Please obtain a fresh Discord token and update the configuration. Authentication failed." instead of 401.

👉 We identified total of 5 accounts that ever received Midjourney CAPTCHA requests over the last 30 days and sent emails to all five account owners, asking them to allow us to use the Midjourney CAPTCHA solver for those accounts. This is still in the early development stage and needs to be properly tested before going public. The Midjourney CAPTCHA solver will be a standard offer to all our subscribers free of charge.

👉 Some of calls to Discord API consistently fail with Cloudflare error code: 1015 (rate-limited on requests), only few accounts affected from what we can tell.
We're have active urgent support case with Cloudflare to investigate this.
If you face this issue please cancel running jobs (they will fail after 30mins anyway) using https://useapi.net/docs/api-v2/get-jobs-cancel, you can get list of currently executing jobs via https://useapi.net/docs/api-v2/get-jobs
At this point Midjourney and other Discord Bot API's are not functional.
We will keep you posted with updates.

🚀 Midjourney and other Discord Bot APIs should be fully functional now.
We are still waiting from Cloudflare to get an update on what's actually happened so we can avoid that in the future.

✨ Still no response from Cloudflare but we identified code which potentially could have triggered Cloudflare rate limiting with error code: 1015 for one of the routes. We will be testing the fix and planning to release it tomorrow.

Added support for Gen-3 Alpha Video to Video
Example

Added support for Gen-3 Alpha Turbo parameter aspect_ratio.
Supported values: landscape (default) and portrait.

We’re proud to announce experimental MiniMax API v1.

MiniMax AI, a Chinese AI startup backed by Alibaba and Tencent. MiniMax unveiled its latest text-to-video AI model at Hailuo AI in early September 2024. This model is notable for generating ultra-realistic video clips with precise prompt following. The best part is that Hailuo AI offers generations free of charge.

Q&A updated to include information about the official Runway/MiniMax API versus our experimental API offerings.

Article Fun with MiniMax API

We added music generation to experimental MiniMax API v1.
Check out MiniMax API Music Samples.

Awesome lyrics by ChatGPT:

In a tech world, we're on the scene,
API connect us, it's a cool routine.

Chat with AI, feel the thrill,
Join the fun, it's the latest skill.

Hey, all the cool kids get it right,
API talkin' day and night.

Tap the future, make it flow,
With AI, let your cool show.

Heads up, faceswap/picsi currently returns 400 : The command has been sent. Please wait for the result to complete.
This is likely due to a recent InsightFaceSwap Discord bot update.
The dev team is aware of the issue and is working on a solution.
✅ Issue was resolved at 3:50PM PST

🚀 We released jobs/seed_async, which will fully replace the deprecated jobs/seed starting November 1, 2024. The newly added jobs/seed_async has a 100% success rate, whereas the now deprecated jobs/seed was failing to retrieve seeds under some obscure conditions.
Please consider switching to use the new version before November 1, 2024.

We created designated Gen-3 Alpha Turbo endpoint and added support for first and last frames.

Original Gen-3 Alpha endpoint will no longer accept turbo and aspect_ratio params starting November 1, 2024.
Please consider switching all turbo load to Gen-3 Alpha Turbo before deadline.

Experimental MiniMax API has been updated to work with hailuoai.video. You will need a Google account to log in to hailuoai.video. Our API supports both free and paid hailuoai.video accounts. The article Fun with MiniMax API has also been updated for your convenience.
Ability to add image in addition to text prompt will be released Monday October 14. 2024.