Prompts in.
Pixels out.
Pixel Factory will serve open image and video models such as Flux and SDXL behind one API, billed per output. Until it launches, run the same models on a GPU by the hour.
Generate images now,
on your own GPU.
Pick a card by the model's memory needs.
Flux.1 [dev]
About 33 GB in BF16 with its text encoders. An RTX PRO 6000 has 96 GB and FP8 support.
RTX PRO 6000FLUX vs SDXL: Image Generation API Costs, GPU Requirements, and the Cheapest Way to Run Both in 2026
DALL-E 3 charges $0.080 per image. Running FLUX.1 Dev on an L40S costs under $0.01 at scale. Here is the full cost math, GPU comparison, and a 10-minute setup guide.
Flux Image Generation on Cloud GPUs: VRAM Requirements, Speed and Cost Per Image (2026)
Flux.1 Dev in FP8 needs 18–23 GB VRAM and generates in 9–10 seconds on an RTX 4090 at $0.39/hr. Full VRAM table for Flux.1 Schnell, Dev, FLUX.2 [klein] 4B and 9B, and every precision level. Real cost per image at packet.ai rates.
ComfyUI in the Cloud: RTX 4090 vs L40S vs A100
One GPU handles Flux in full precision without breaking a sweat. Another runs out of memory halfway through. Here's exactly which card your ComfyUI workflow needs.
Your next run
starts at $0.39.
Sign up, top up, launch. You'll be on a GPU in minutes.