Will It Run AI
black forest labs

Flux.1 Fill Dev

Frontier

by Black Forest Labs

Inpainting and outpainting specialist built on the Flux.1 architecture. Designed for masked region generation — object removal, replacement, and image extension. Uses higher guidance scale (30) and more steps (50) than standard Flux.1 Dev for optimal mask adherence.

VRAM requirements, GPU fit, and setup notes for Flux.1 Fill Dev, including 8GB/12GB fit guidance where relevant. Recommended runtimes: ComfyUI and Diffusers support. Best download size: ~23.8 GB at FP16.

  • Inpainting and outpainting specialist
  • Seamless object removal and replacement
  • Same quality as Flux.1 Dev for masked regions
  • Requires mask input alongside text prompt
ComfyUI, DiffusersFP16 safetensors

Your hardware

Detecting...

Parameters12B
Max Resolution1024×1024
Default Steps50
ArchitectureDIT
Licenseflux-1-dev-non-commercial

Image Quality Benchmarks

Measured quality metrics for Flux.1 Fill Dev outputs.

Human Preference Score92%

How often humans prefer this model's output (0-100%)

Aesthetic Score8.0

Visual quality and composition rating (5-9 scale)

VRAM Requirements by Resolution and Precision

Compare which GPUs can run Flux.1 Fill Dev at different precisions. FP8 uses less memory than FP16 when available, and the grade shows how comfortably each GPU handles the workload.

FP16 (full precision)

ResolutionVRAM RequiredRTX 4090 24GBRTX 3060 12GBRTX 4060 8GBMacBook Pro M4 Pro 24GB
512×51231.5 GBDFFF
768×76831.7 GBDFFF
1024×102432.0 GBDFFF

Optimization Tips

Turbo / LCM distillation

Use distilled scheduler at 4-8 steps for faster iteration

Run with Python

Run with Python (diffusers)
from diffusers import FluxPipeline
import torch

pipe = FluxPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-Fill-dev",
    torch_dtype=torch.float16
)
pipe.to("cuda")

image = pipe(
    prompt="your prompt here",
    num_inference_steps=50,
    guidance_scale=3.5,
    height=1024,
    width=1024,
).images[0]
image.save("output.png")

Get started

Setup instructions for running Flux.1 Fill Dev locally

1. Download the model

Get the checkpoint from HuggingFace

2. Place in:

ComfyUI/models/checkpoints/

3. Launch ComfyUI

python main.py

Memory Breakdown

VRAM allocation at 1024×1024 on RTX 4090 24GB (24 GB)

Required: 32.0 GBAvailable: 24.0 GB
Weights24.0 GB
VAE0.2 GB
Text Encoder9.6 GB
Activations0.8 GB
Overhead0.5 GB

Estimated Generation Time

Time per image at 1024×1024, 28 steps, FP16.

RTX 4090 24GB~17s
RTX 3060 12GB~1m 4s
RTX 4060 8GB~1m 37s
MacBook Pro M4 Pro 24GB~2m 18s

Sample Outputs

Available Formats, Downloads & Setup

Download Flux.1 Fill Dev in the precision that matches your GPU. Lower precision usually means less VRAM pressure, while higher precision keeps more quality.

FormatoPrecisãoTamanhoProvedor
safetensorsRecomendadoFP1623.8 GBofficialBaixar

LoRA Ecosystem

small

Flux Fill is an inpainting/outpainting model derived from Flux Dev. Compatible with Flux Dev LoRAs, though results may vary since the model is fine-tuned for fill tasks.

Approximately 50 LoRAs available on CivitAI. Each LoRA adds ~0.3 GB VRAM.

Popular LoRAs for Flux.1 Fill Dev

NameCategoryDownloads
Flux Realism LoRAstyle200KView
Browse all LoRAs on CivitAI

Related Workflows

You might also like

Frequently asked questions

FAQ — Flux.1 Fill Dev VRAM, Runtimes & Fit

How much VRAM does Flux.1 Fill Dev need?

Flux.1 Fill Dev (12B parameters) requires approximately 32.0 GB of VRAM at FP16 precision for standard 1024×1024 image generation. If you want a lighter setup, lower precisions like FP8 can reduce memory use when available.

Can I run Flux.1 Fill Dev on an 8GB GPU?

Flux.1 Fill Dev usually needs more than 8GB for comfortable local use. Check the VRAM table above for the exact resolution and precision trade-off.

Does Flux.1 Fill Dev work in ComfyUI and Diffusers?

Flux.1 Fill Dev is marked for ComfyUI and Diffusers support in our catalog, so those are the runtimes we recommend first for local setup. If your workflow uses another front end, check the model's available formats and workflow notes above before downloading.

Can I run Flux.1 Fill Dev on RTX 4090?

Flux.1 Fill Dev is too large for the RTX 4090's 24 GB VRAM at FP16. Consider using FP8 precision or a GPU with more VRAM.

Does Flux.1 Fill Dev support ControlNet?

There are currently no known ControlNet adapters for Flux.1 Fill Dev. Check Hugging Face and Civitai for community-contributed adapters.

Does Flux.1 Fill Dev have LoRA support?

Flux Fill is an inpainting/outpainting model derived from Flux Dev. Compatible with Flux Dev LoRAs, though results may vary since the model is fine-tuned for fill tasks. The LoRA ecosystem for Flux.1 Fill Dev is rated as "small". There are approximately 50 LoRAs available on Civitai. Each LoRA adds roughly 0.3 GB of extra VRAM.

How fast is Flux.1 Fill Dev?

On a reference GPU (RTX 4090 24GB), Flux.1 Fill Dev generates a 1024×1024 image in approximately ~17s at FP16 with 28 inference steps. Faster GPUs with higher memory bandwidth will produce images more quickly.

About Flux.1 Fill Dev

Use cases
inpaintingoutpaintingimage-editing
Recommended runtimes
comfyuidiffusers

See also