Comfy-Org / text-to-image Open weights updated 1 week ago

Flux-1-Dev

πŸ“‚ ComfyUI/ β”œβ”€β”€ πŸ“‚ models/ β”‚ β”œβ”€β”€ πŸ“‚ checkpoints/ β”‚ β”‚ β”œβ”€β”€ flux1-dev-fp8.safetensors β”‚ β”‚ └── flux1-dev.safetensors β”‚ β”œβ”€β”€ πŸ“‚ diffusionmodels/ β”‚ β”‚ β”œβ”€β”€ flux1-canny-dev.safetensors β”‚ β”‚ β”œβ”€β”€ flux1-depth-dev-nvfp4.safetensors β”‚ β”‚ └── flux1-fill-dev.safetensors β”‚ β”œβ”€β”€ πŸ“‚ loras/ β”‚ β”‚ └── flux1-depth-dev-lora.safetensors

Params
11.9 B
Context
β€”
Downloads 30d
1.3 M
Likes
713
Licence: other Not gated SAFETENSORS View on Hugging Face β†—

Download history

daily snapshots Β· 14 days
1.3 M1.1 M
Oct 28Nov 1Nov 6Nov 10

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 Β· 24 GB
model.safetensors fp16 98.8 GB 110.9 GB ❌ Won’t fit
Estimate: file size Γ— 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark β€” how we calculate this.

Specifications

Parameters
11.9 B
Licence
other
First seen on the Hub
2024-08-03
Base model
FLUX.1-dev
Training datasets
undisclosed
Added to our catalog
2026-10-28

Family

Base model and the most-downloaded derivatives in the catalog.

Compare with any text-to-image model