FLUX.2 Dev Full
FLUX.2 is Black Forest Labs’ image model family with multi-image editing support. The catalog includes full and quantized configurations with different memory requirements. Review the selected workflow and GPU before launch.
- GPU tier
- GPU Very High VRAM (A100 80GB)
- Estimated customer rate
- $1.85/hr
- VRAM
- 80GB
- Template
- comfyui-flux2
HiDream I1 Dev FP8
HiDream I1 is a 17B image generation model family. The catalog includes Dev, Full and Fast variants with FP8 configurations for text-to-image workflows. Prompt following and fine details still require output review.
- GPU tier
- GPU High VRAM (A6000)
- Estimated customer rate
- $0.72/hr
- VRAM
- 48GB
- Template
- comfyui-hidream
Deployment facts
| Factor | FLUX.2 Dev Full | HiDream I1 Dev FP8 |
|---|---|---|
| Model family | flux2 | hidream |
| Variant | Dev Full (64GB) | Dev FP8 (Recommended) |
| Type | image | image |
| Deployment template | comfyui-flux2 | comfyui-hidream |
| GPU tier | GPU Very High VRAM (A100 80GB) | GPU High VRAM (A6000) |
| GPU | NVIDIA A100 80GB PCIe | NVIDIA RTX A6000 |
| VRAM | 80GB | 48GB |
| vCPU / RAM / disk | 8 vCPU / 117GB RAM / 300GB disk | 9 vCPU / 50GB RAM / 200GB disk |
| Estimated customer rate | $1.85/hr | $0.72/hr |
| Estimated 730-hour month | $1348/mo | $522/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 | FLUX.2 Dev Full | HiDream I1 Dev FP8 |
|---|---|---|---|
| Prototype | 40 | $73.84 | $28.60 |
| Part-time app | 160 | $295 | $114 |
| Always-on | 730 | $1348 | $522 |
What this comparison covers
- FLUX.2 Dev Full: 80GB GPU memory, estimated $1.85/hr including configured disk and the service fee.
- HiDream I1 Dev FP8: 48GB GPU memory, estimated $0.72/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 | FLUX.2 Dev Full | HiDream I1 Dev FP8 | Lower cost or requirement |
|---|---|---|---|
| Lower estimated customer rate | $1.85/hr | $0.72/hr | HiDream I1 Dev FP8 |
| Lower VRAM requirement | 80GB | 48GB | HiDream I1 Dev FP8 |
| Cheaper always-on deployment | $1348/mo | $522/mo | HiDream I1 Dev FP8 |
FAQ
Which is cheaper to run, FLUX.2 Dev Full or HiDream I1 Dev FP8?
HiDream I1 Dev FP8 has the lower estimated customer rate at $0.72/hr, including configured disk and the ModelPilot service fee. Startup is billed; retained storage and configuration changes can affect your total.
Which uses less VRAM, FLUX.2 Dev Full or HiDream I1 Dev FP8?
HiDream I1 Dev FP8 maps to the lower VRAM tier at 48GB 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.