DEV Community: beihuang

MiniMax-H3 image-to-video pitfalls: don't mix first_frame and reference_image

beihuang — Thu, 05 Nov 2026 06:43:42 +0000

I recently drove MiniMax-H3 through an OpenAI-compatible media gateway to generate a 15s, 9:16, with-audio vertical clip from a first frame plus a long storyboard prompt. I burned a few jobs on avoidable mistakes. Notes below are reproducible and sanitized.

Field names follow the gateway docs; treat this as a debugging checklist, not a product pitch.

Pitfall 1: Don't mix frame and reference roles

Sending both:

first_frame (image-to-video from a start frame)
reference_image (identity / reference mode)

got an upstream error like:

frame and reference roles cannot be mixed

Takeaway: pick one mode. If the product docs describe both capabilities, the call layer still must not "just include everything."

Pitfall 2: Skip undocumented `images=@…` fields

Some copy-pasted examples use images=@file. On this path that returned unsupported / unexpected file field errors.

Use the documented multipart fields instead:

first_frame, or
reference_image

Public aspect field name is ratio, not aspect_ratio.

Pitfall 3: `prompt optimization failed` vs first-frame resolution

What I saw:

First frame around 1008×1792: even a short clean English prompt could fail with prompt optimization failed
Same account, text-to-video only: succeeded — so it wasn't obviously a dead key or zero balance
Re-encoding the first frame to 720×1280 JPEG, same other params: two runs in a row completed

Suggested order when debugging:

Confirm you didn't mix frame / reference
Confirm multipart field names match the docs
Downscale / re-encode the first frame to ~720×1280 and retry
Only then chase upstream status and poll payloads

A working combo (sanitized)

Item	Value
model	MiniMax-H3
seconds	15
ratio	9:16
resolution	768P
input	`first_frame` only (re-encoded vertical JPEG)
avoid	`reference_image`, undocumented `images`

Typical async flow: POST /v1/videos → poll GET /v1/videos/{id} → download with GET /v1/videos/{id}/content. Status JSON may not include a durable direct URL; the content endpoint is more reliable. Prefer a unique Idempotency-Key on multipart creates.

Bonus: DeepSeek Flash queueing vs own capacity

Separately, when a lot of clients share the same official DeepSeek / Kimi queues, TTFT spikes show up as "everything is slow" even if your gateway is healthy. Comparing a route that does not share the crowded official pool (own / reserved capacity) against a shared proxy is a useful A/B when peak-hour latency looks broken everywhere.

Use public model ids (not marketing names) in the request body. For this gateway the public flash alias maps to the catalog id you see in docs / /llms.txt.

Soft wrap-up

First frame ≠ reference image — never both.
Field names follow the docs — don't transplant another SDK's images.
I2V + prompt optimization failed — resize the first frame before blaming the prompt.
Peak latency — check whether you're on a shared official queue.

References (docs + copy-paste examples):

API docs: https://cheapbuddy.cc/api-docs
Bash / Python / Node examples: https://github.com/GiantClam/cheapbuddy-examples
Model list for agents: https://cheapbuddy.cc/llms.txt

If you hit a similar 400, paste the error text + field names (no keys) in the comments and we can compare notes.

How to Remove Image Backgrounds in 3 Seconds with AI

beihuang — Thu, 11 Jun 2026 02:30:12 +0000

A practical, no-fluff guide. If you need to remove image backgrounds without paying for expensive tools, this is for you.

Why this matters

Background removal used to require Photoshop skills and 20 minutes per image. Now it takes 3 seconds — and zero skill.

Most people reach for a paid service like remove.bg or Photoshop. Both work, but they:

Require sign-up
Have daily limits
Cost $9–$200/month

There's a better way.

The 3 Seconds solution

Modern AI runs entirely in your browser. No server, no upload, no waiting room.

Here's the step-by-step:

Step 1: Open Remove Anything

Go to https://remove-anything.com. No sign-up, no credit card.

Step 2: Upload your image (JPG/PNG/WebP)

Drag-and-drop your file (or paste from clipboard). AI works in the browser — your image never leaves your device.

Step 3: Click the button

Click the button. Wait 3 Seconds.

Step 4: Download

Right-click → Save. Or use the copy button. Done.

What you get

✅ Free, unlimited uses
✅ Works on any modern browser
✅ Privacy-first (no upload to server)
✅ AI background removal
✅ AI object removal

Try it yourself

→ https://remove-anything.com

I built Remove Anything because I got tired of hitting paywalls on tools that should be free. If it saves you 10 minutes today, I count that as a win.

Wang Xinjin builds Remove Anything. Follow for more AI image tools / SaaS tools that respect your time and wallet.

3 Steps to Perfect Photos: Upload, Paint, Download!

beihuang — Thu, 21 Aug 2025 06:20:29 +0000

Remove unwanted objects, people, text, and flaws effortlessly with our AI-powered eraser tool. No skills needed—just paint and erase. Enjoy HD quality, fast processing, and free downloads without watermarks.

Perfect for photographers, social media users, and online sellers. Try it now and transform your images in seconds!

Pleace find https://www.remove-anything.com/en