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.
Your hardware
Detecting...
Measured quality metrics for Flux.1 Fill Dev outputs.
How often humans prefer this model's output (0-100%)
Visual quality and composition rating (5-9 scale)
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.
| Resolution | VRAM Required | RTX 4090 24GB | RTX 3060 12GB | RTX 4060 8GB | MacBook Pro M4 Pro 24GB |
|---|---|---|---|---|---|
| 512×512 | 31.5 GB | D● | F● | F● | F● |
| 768×768 | 31.7 GB | D● | F● | F● | F● |
| 1024×1024 | 32.0 GB | D● | F● | F● | F● |
Turbo / LCM distillation
Use distilled scheduler at 4-8 steps for faster iteration
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.pyVRAM allocation at 1024×1024 on RTX 4090 24GB (24 GB)
Time per image at 1024×1024, 28 steps, FP16.
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.
| Format | Precision | Size | Provider | |
|---|---|---|---|---|
| safetensorsRecommended | FP16 | 23.8 GB | official | Download |
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.
| Name | Category | Downloads | |
|---|---|---|---|
| Flux Realism LoRA | style | 200K | View |
Frequently asked questions
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.
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.
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.
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.
There are currently no known ControlNet adapters for Flux.1 Fill Dev. Check Hugging Face and Civitai for community-contributed adapters.
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.
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.
See also