---
base_model: black-forest-labs/FLUX.1-Fill-dev
license: other
license_name: flux-1-dev-non-commercial-license
license_link: LICENSE.md
model_creator: black-forest-labs
model_name: FLUX.1-Fill-dev
quantized_by: Second State Inc.
language:
- en
tags:
- text-to-image
- image-generation
- flux
---

<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->

> [!CAUTION]
> T5, Clip, and ae are still not provided in the original model

# FLUX.1-Fill-dev-GGUF

## Original Model

[black-forest-labs/FLUX.1-Fill-dev](https://huggingface.co/black-forest-labs/FLUX.1-Fill-dev)

## Run with LlamaEdge-StableDiffusion

- Version: coming soon

<!-- - Version: [0.1.4](https://github.com/LlamaEdge/sd-api-server/releases/tag/0.1.4)

- Run as LlamaEdge service

  ```bash
  wasmedge --dir .:. sd-api-server.wasm \
    --model-name flux1-fill-dev \
    --diffusion-model flux1-fill-dev-Q4_0.gguf \
    --vae ae.safetensors \
    --clip-l clip_l.safetensors \
    --t5xxl t5xxl-Q8_0.gguf
  ```

  - Run with LoRA

    Assume that the LoRA model is located in the `lora-models` directory

    ```bash
    wasmedge --dir .:. \
      --dir lora-models:lora-models \
      sd-api-server.wasm \
      --model-name flux1-fill-dev \
      --diffusion-model flux1-fill-dev-Q4_0.gguf \
      --vae ae.safetensors \
      --clip-l clip_l.safetensors \
      --t5xxl t5xxl-Q8_0.gguf \
      --lora-model-dir lora-models
    ```

    *For details, see https://github.com/LlamaEdge/sd-api-server/blob/main/examples/flux_with_lora.md* -->

## Quantized GGUF Models

| Name | Quant method | Bits | Size | Use case |
| ---- | ---- | ---- | ---- | ----- |
| [ae.safetensors](https://huggingface.co/second-state/FLUX.1-Fill-dev-GGUF/blob/main/ae.safetensors) | f32 | 32 | 335 MB | |
| [flux1-fill-dev-Q2_K.gguf](https://huggingface.co/second-state/FLUX.1-Fill-dev-GGUF/blob/main/flux1-fill-dev-Q2_K.gguf) | Q2_K | 2 | 4.16 GB | |
| [flux1-fill-dev-Q3_K.gguf](https://huggingface.co/second-state/FLUX.1-Fill-dev-GGUF/blob/main/flux1-fill-dev-Q3_K.gguf) | Q2_K | 2 | 5.36 GB | |
| [flux1-fill-dev-Q4_0.gguf](https://huggingface.co/second-state/FLUX.1-Fill-dev-GGUF/blob/main/flux1-fill-dev-Q4_0.gguf) | Q4_0 | 4 | 6.93 GB | |
| [flux1-fill-dev-Q4_1.gguf](https://huggingface.co/second-state/FLUX.1-Fill-dev-GGUF/blob/main/flux1-fill-dev-Q4_1.gguf) | Q4_1 | 4 | 7.67 GB | |
| [flux1-fill-dev-Q4_K.gguf](https://huggingface.co/second-state/FLUX.1-Fill-dev-GGUF/blob/main/flux1-fill-dev-Q4_K.gguf) | Q4_K | 4 | 6.93 GB | |
| [flux1-fill-dev-Q5_0.gguf](https://huggingface.co/second-state/FLUX.1-Fill-dev-GGUF/blob/main/flux1-fill-dev-Q5_0.gguf) | Q5_0 | 5 | 8.41 GB | |
| [flux1-fill-dev-Q5_1.gguf](https://huggingface.co/second-state/FLUX.1-Fill-dev-GGUF/blob/main/flux1-fill-dev-Q5_1.gguf) | Q5_1 | 5 | 9.15 GB | |
| [flux1-fill-dev-Q8_0.gguf](https://huggingface.co/second-state/FLUX.1-Fill-dev-GGUF/blob/main/flux1-fill-dev-Q8_0.gguf) | Q8_0 | 8 | 12.8 GB | |
| [flux1-fill-dev.safetensors](https://huggingface.co/second-state/FLUX.1-Fill-dev-GGUF/blob/main/flux1-fill-dev.safetensors)   | f16 | 16 | 23.8 GB | |

**Quantized with stable-diffusion.cpp `master-c3eeb669`.**