Stable Diffusion WebUI (A1111)
AUTOMATIC1111 Stable Diffusion WebUI on port 7860, plus SSH.
| Detail | Value |
|---|---|
| Image | ghcr.io/fairgpu/sd-webui:latest |
| Mode | interactive |
| Ports | 22/ssh, 7860/http |
| Needs | 6 GB VRAM, 30 GB disk |
| Compatible machines online | 1 |
| Used | 0 times |
Stable Diffusion WebUI (AUTOMATIC1111)
Opens on port 7860. Put checkpoints in /workspace/stable-diffusion-webui/models/Stable-diffusion.
- VRAM: 6 GB minimum (SD 1.5), 12 GB+ for SDXL.
- Launch flags via
WEBUI_ARGS(defaults include--api, so the REST API is on the same port).
Before you stop
Everything you create lives inside the container on the host's disk and is removed when the rental ends. Push results out before stopping (scp, rsync, git, HF Hub, S3...). From inside the container you can run fairgpu extend 60 to add time, fairgpu mark "epoch 3 done" to annotate the timeline and fairgpu stop when you are done.
Step by step
1. Open the WebUI
Click the SD WebUI port once it is green. The REST API is on the same port (/docs) because the template starts with --api.
2. Add checkpoints and LoRAs
cd /workspace/stable-diffusion-webui/models/Stable-diffusion
wget -O realisticVision.safetensors "<direct download URL from Civitai or Hugging Face>"
ls /workspace/stable-diffusion-webui/models/Lora
Click the refresh icon next to the checkpoint dropdown. Models stay in /workspace between rentals on the same host (persistent workspace) or anywhere via a checkpoint.
3. Extensions
Install from the Extensions tab or git clone into /workspace/stable-diffusion-webui/extensions, then Apply and restart UI.
4. Generate from a script
curl -s http://<relay>:<port>/sdapi/v1/txt2img -H 'content-type: application/json' -d '{"prompt":"a lighthouse at dawn","steps":25}' | jq -r '.images[0]' | base64 -d > out.png
5. Low VRAM
6-8 GB cards: add --medvram (or --lowvram) to WEBUI_ARGS; 12 GB+ for SDXL. Outputs are in /workspace/stable-diffusion-webui/outputs.
Save your results before you stop
- Everything outside
/workspacedisappears when the rental stops;/workspacesurvives on the same host (persistent workspace) and anywhere with a FairGPU checkpoint. - Save checkpoint now on the rental page (or
fairgpu snapshot save "label"inside the container) archives /workspace to FairGPU cloud storage; Download workspace gets it to your computer. scp -P <port> root@<relay>:/workspace/results ./copies files out over SSH;rsyncand SFTP (WinSCP/FileZilla) work the same way.- Stop the rental to stop billing. Set an idle auto-stop if you tend to forget, or buy the $0.99 finish alert (SMS + email).
Machines that can run it
| Machine | GPU | VRAM | Price | Status | Reliability | Country | Host | Cached |
|---|---|---|---|---|---|---|---|---|
| WhiteBob | NVIDIA GeForce RTX 5060 Ti | 16 GB | $0.10/hr | available now | 62 % | - | Aharon Sela | - |