Stable Diffusion 3.5 Medium
Stable Diffusion is an image generation family from Stability AI with community fine-tunes and LoRAs. The catalog includes SDXL, SD 3.5 and SD 1.5 configurations. Choose a compatible model, workflow and license for your project.
- GPU tier
- GPU Efficient (L4)
- Estimated customer rate
- $0.66/hr
- VRAM
- 24GB
- Template
- comfyui-dynamic
Stable Diffusion 3.5 Turbo
Stable Diffusion is an image generation family from Stability AI with community fine-tunes and LoRAs. The catalog includes SDXL, SD 3.5 and SD 1.5 configurations. Choose a compatible model, workflow and license for your project.
- GPU tier
- GPU Efficient (L4)
- Estimated customer rate
- $0.66/hr
- VRAM
- 24GB
- Template
- comfyui-dynamic
Deployment facts
| Factor | Stable Diffusion 3.5 Medium | Stable Diffusion 3.5 Turbo |
|---|---|---|
| Model family | stable-diffusion | stable-diffusion |
| Variant | Medium | Turbo |
| Type | image | image |
| Deployment template | comfyui-dynamic | comfyui-dynamic |
| GPU tier | GPU Efficient (L4) | GPU Efficient (L4) |
| GPU | NVIDIA L4 | NVIDIA L4 |
| VRAM | 24GB | 24GB |
| vCPU / RAM / disk | 12 vCPU / 50GB RAM / 200GB disk | 12 vCPU / 50GB RAM / 200GB disk |
| Estimated customer rate | $0.66/hr | $0.66/hr |
| Estimated 730-hour month | $484/mo | $484/mo |
| Paid launch | Available; review setup before launch | Available; review setup before launch |
Estimates use the same rate as the model catalog, including configured disk and the ModelPilot service fee. GPU time is billed during startup and while allocated. Configuration changes and retained storage can affect your total; review the launch details before paying.
Cost scenarios
| Usage level | Hours/mo | Stable Diffusion 3.5 Medium | Stable Diffusion 3.5 Turbo |
|---|---|---|---|
| Prototype | 40 | $26.52 | $26.52 |
| Part-time app | 160 | $106 | $106 |
| Always-on | 730 | $484 | $484 |
What this comparison covers
- Stable Diffusion 3.5 Medium: 24GB GPU memory, estimated $0.66/hr including configured disk and the service fee.
- Stable Diffusion 3.5 Turbo: 24GB GPU memory, estimated $0.66/hr including configured disk and the service fee.
- Review each template’s required input files, model downloads and manual setup steps before launching.
- Dedicated GPU time is billed during startup and while allocated. Retained storage can remain billable after stopping.
- These are deployment comparisons, not output-quality benchmarks. Test representative inputs and review the results for your project.
Configuration differences
| Factor | Stable Diffusion 3.5 Medium | Stable Diffusion 3.5 Turbo | Lower cost or requirement |
|---|---|---|---|
| Lower estimated customer rate | $0.66/hr | $0.66/hr | Tie |
| Lower VRAM requirement | 24GB | 24GB | Tie |
| Cheaper always-on deployment | $484/mo | $484/mo | Tie |
FAQ
Which is cheaper to run, Stable Diffusion 3.5 Medium or Stable Diffusion 3.5 Turbo?
Both use the same estimated customer rate of $0.66/hr, including configured disk and the ModelPilot service fee.
Which uses less VRAM, Stable Diffusion 3.5 Medium or Stable Diffusion 3.5 Turbo?
Stable Diffusion 3.5 Medium maps to the lower VRAM tier at 24GB in the current deployment recommendation.
Can both models run through ModelPilot?
Both have a deployment option in the catalog. Review each model's setup requirements, available GPU and estimated rate before launching. Output quality depends on the model, input and workflow.