Set up your own image generator

About 15 minutes of clicking, then about 15–30 minutes of waiting. No coding. You need a card to add $10 of RunPod credit — you pay only while pictures are being made, nothing while it sits idle.

Tick each step as you go — this page remembers where you are.

Make three accounts

• GitHub — holds your copy of the generator.

• Civitai — where most models come from. Needed if the worker’s page asks for a Civitai token.

• RunPod — the computer that makes the pictures. Then Billing → add $10.

  This is a referral link: after your first $10, RunPod gives you a bonus credit (usually $5–10) and Cobalt Pear a small credit.

Copy the worker

A «worker» is the model packed for RunPod. Each model has its own worker page on GitHub — its page links here.

1. On the worker’s GitHub page, click the green Use this template → Create a new repository.
2. Any name is fine. Choose Private → Create repository.

Keep the worker’s own page address — you paste it into Cobalt Pear in the last step (not the address of your copy).

No worker yet? Start with a model from the app’s Models list (like Z-Image Turbo) — it needs no GitHub at all: skip to the quick start below, then make the API key.

Quick start: a model from the list, without GitHub

1. Open Cobalt Pear → Models → Add next to the model. The RunPod steps show in the same window.
2. Do those steps on RunPod — for Z-Image Turbo: Serverless → New Endpoint → Deploy image or video API → Text To Image → Tongyi-MAI/Z-Image-Turbo → Deploy with vLLM Omni → Next → Create Endpoint.
3. In the endpoint’s settings set Max workers 1, Execution timeout 600 → Save.
4. Paste its endpoint ID next to the model in Cobalt Pear. Then make an API key and put it in Settings.

No build to wait for. The first picture takes about a minute while RunPod starts it; then about 8 seconds each.

Put your Civitai token in your copy

Only if the worker’s page asks for it. It lets RunPod download the model with your account.

1. Civitai → your picture (top right) → Account settings → Security & Apps → API Keys → Add API key → Permission preset Read Only → copy it and keep it somewhere — Civitai shows it only once. One token works for every model: next time, reuse it.
2. In your copy on GitHub, click Dockerfile → the pencil ✏️ (top right of the file).
3. Replace PASTE_YOUR_CIVITAI_TOKEN_HERE with your token → Commit changes… → Commit changes again.

Create the endpoint

The «endpoint» is your generator on RunPod.

1. RunPod → Serverless → New Endpoint → Deploy from a GitHub repository.
2. Pick your copy. The first time, click Edit connection and let RunPod see it.
3. Change only these. Leave everything else as it is — RunPod’s defaults are right:

Setting	Value
GPU configuration	tick 16 GB for SDXL, Pony, Illustrious, NoobAI and SD 1.5 · 24 GB for Krea 2, FLUX.1, Chroma, Z-Image and bigger · more boxes = easier to get a GPU
Max workers	1
Advanced settings → Enable FlashBoot	switch on — later starts are much faster
→ Container configuration → Container disk	20 GB for SDXL, Pony, Illustrious, NoobAI and SD 1.5 · 30 GB for A1111 workers · 40 GB for Krea 2, FLUX.1, Chroma, Z-Image and bigger

4. Click Deploy at the bottom.

RunPod may warn «runpod.serverless.start() handler not found in your repo». You can ignore it — the worker starts its handler from the image it builds on.

Wait for the build

RunPod now builds your generator — about 15 minutes (it stops a build at 30). The endpoint’s page shows its progress. You can make the API key meanwhile.

If it fails, open the build log, copy the last lines and ask in Discussions.

Make an API key

1. RunPod → Settings → API Keys → Create API Key.
2. Choose All.
3. Copy the key now — RunPod shows it only once.

One key does everything — making pictures and making endpoints — for every endpoint you add later. Cobalt Pear keeps it in your browser, so use a browser only you use. RunPod spends only the credit you added.

Connect Cobalt Pear

1. Open Cobalt Pear → Models → paste the worker’s page address (from Copy the worker) under «Your own worker» → Add.
2. Paste your endpoint ID next to the model — on RunPod it is the short code under the endpoint’s name (like ab12cd34ef56gh), then go to Chat.
3. Type what you want to see, press Enter. The first time it opens Settings — paste your RunPod API key there, then go back to Chat.

The very first picture can take a few minutes (up to about 12) while RunPod starts the generator for the first time. After that it is seconds to a minute.

Next: add a LoRA, or pick another model.

When something is off

«Wrong RunPod key»	Check the key, and that it has All access.
Waits a long time	Normal for the first picture, and after a long break. If it never starts, check the endpoint’s page on RunPod.
To stop paying entirely	Set Max workers to 0, or delete the endpoint. Idle endpoints with 0 active workers cost nothing.
Anything else	Ask in Discussions.