Instructions to use unsloth/FLUX.1-dev-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- Unsloth Desktop
|
Download README.md from unsloth/FLUX.1-dev-FP8: direct link, hf CLI and curl.
- Browser
- Download file 8.05 kB
-
https://huggingface.co/unsloth/FLUX.1-dev-FP8/resolve/main/README.md
- Command line
-
hf download hf://unsloth/FLUX.1-dev-FP8/README.md
-
curl -L -o README.md https://huggingface.co/unsloth/FLUX.1-dev-FP8/resolve/main/README.md
8.05 kB
| base_model: black-forest-labs/FLUX.1-dev | |
| language: | |
| - en | |
| license: other | |
| license_name: flux-1-dev-non-commercial-license | |
| license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md | |
| extra_gated_prompt: By clicking "Agree", you agree to the [FluxDev Non-Commercial | |
| License Agreement](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md) | |
| and acknowledge the [Acceptable Use Policy](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/POLICY.md). | |
| tags: | |
| - fp8 | |
| - unsloth | |
| - quantized | |
| - text-to-image | |
| - image-generation | |
| - flux | |
| widget: | |
| - text: cute sloth typing on a computer (INT8) | |
| output: | |
| url: samples/int8_1.png | |
| - text: cute sloth typing on a computer (INT8) | |
| output: | |
| url: samples/int8_2.png | |
| - text: cute sloth typing on a computer (FP8) | |
| output: | |
| url: samples/fp8_1.png | |
| - text: cute sloth typing on a computer (FP8) | |
| output: | |
| url: samples/fp8_2.png | |
| pipeline_tag: text-to-image | |
| This is an FP8 / INT8 quantized version of [FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev). <br> | |
| - Optimized for efficient inference with reduced memory footprint. Same-seed LPIPS vs the bf16 model (lower is better): 0.125 INT8, 0.134 FP8. | |
| <div> | |
| <div style="display: flex; gap: 5px; align-items: center; "> | |
| <a href="https://github.com/unslothai/unsloth/"> | |
| <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133"> | |
| </a> | |
| <a href="https://discord.gg/unsloth"> | |
| <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173"> | |
| </a> | |
| <a href="https://docs.unsloth.ai/"> | |
| <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143"> | |
| </a> | |
| </div> | |
| </div> | |
| --- | |
| ### Samples | |
| Prompt: "cute sloth typing on a computer" | |
| <table> | |
| <tr> | |
| <td align="center"><b>INT8</b></td> | |
| <td align="center"><b>INT8</b></td> | |
| </tr> | |
| <tr> | |
| <td><img src="samples/int8_1.png" width="300"></td> | |
| <td><img src="samples/int8_2.png" width="300"></td> | |
| </tr> | |
| <tr> | |
| <td align="center"><b>FP8</b></td> | |
| <td align="center"><b>FP8</b></td> | |
| </tr> | |
| <tr> | |
| <td><img src="samples/fp8_1.png" width="300"></td> | |
| <td><img src="samples/fp8_2.png" width="300"></td> | |
| </tr> | |
| </table> | |
| --- | |
| ![FLUX.1 [dev] Grid](./dev_grid.jpg) | |
| `FLUX.1 [dev]` is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. | |
| For more information, please read our [blog post](https://blackforestlabs.ai/announcing-black-forest-labs/). | |
| # Key Features | |
| 1. Cutting-edge output quality, second only to our state-of-the-art model `FLUX.1 [pro]`. | |
| 2. Competitive prompt following, matching the performance of closed source alternatives . | |
| 3. Trained using guidance distillation, making `FLUX.1 [dev]` more efficient. | |
| 4. Open weights to drive new scientific research, and empower artists to develop innovative workflows. | |
| 5. Generated outputs can be used for personal, scientific, and commercial purposes as described in the [`FLUX.1 [dev]` Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md). | |
| # Usage | |
| We provide a reference implementation of `FLUX.1 [dev]`, as well as sampling code, in a dedicated [github repository](https://github.com/black-forest-labs/flux). | |
| Developers and creatives looking to build on top of `FLUX.1 [dev]` are encouraged to use this as a starting point. | |
| ## API Endpoints | |
| The FLUX.1 models are also available via API from the following sources | |
| - [bfl.ml](https://docs.bfl.ml/) (currently `FLUX.1 [pro]`) | |
| - [replicate.com](https://replicate.com/collections/flux) | |
| - [fal.ai](https://fal.ai/models/fal-ai/flux/dev) | |
| - [mystic.ai](https://www.mystic.ai/black-forest-labs/flux1-dev) | |
| ## ComfyUI | |
| `FLUX.1 [dev]` is also available in [Comfy UI](https://github.com/comfyanonymous/ComfyUI) for local inference with a node-based workflow. | |
| ## Diffusers | |
| To use `FLUX.1 [dev]` with the 🧨 diffusers python library, first install or upgrade diffusers | |
| ```shell | |
| pip install -U diffusers | |
| ``` | |
| Then you can use `FluxPipeline` to run the model | |
| ```python | |
| import torch | |
| from diffusers import FluxPipeline | |
| pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16) | |
| pipe.enable_model_cpu_offload() #save some VRAM by offloading the model to CPU. Remove this if you have enough GPU power | |
| prompt = "A cat holding a sign that says hello world" | |
| image = pipe( | |
| prompt, | |
| height=1024, | |
| width=1024, | |
| guidance_scale=3.5, | |
| num_inference_steps=50, | |
| max_sequence_length=512, | |
| generator=torch.Generator("cpu").manual_seed(0) | |
| ).images[0] | |
| image.save("flux-dev.png") | |
| ``` | |
| To learn more check out the [diffusers](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux) documentation | |
| --- | |
| # Limitations | |
| - This model is not intended or able to provide factual information. | |
| - As a statistical model this checkpoint might amplify existing societal biases. | |
| - The model may fail to generate output that matches the prompts. | |
| - Prompt following is heavily influenced by the prompting-style. | |
| # Out-of-Scope Use | |
| The model and its derivatives may not be used | |
| - In any way that violates any applicable national, federal, state, local or international law or regulation. | |
| - For the purpose of exploiting, harming or attempting to exploit or harm minors in any way; including but not limited to the solicitation, creation, acquisition, or dissemination of child exploitative content. | |
| - To generate or disseminate verifiably false information and/or content with the purpose of harming others. | |
| - To generate or disseminate personal identifiable information that can be used to harm an individual. | |
| - To harass, abuse, threaten, stalk, or bully individuals or groups of individuals. | |
| - To create non-consensual nudity or illegal pornographic content. | |
| - For fully automated decision making that adversely impacts an individual's legal rights or otherwise creates or modifies a binding, enforceable obligation. | |
| - Generating or facilitating large-scale disinformation campaigns. | |
| # License | |
| This model falls under the [`FLUX.1 [dev]` Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md). | |
| --- | |
| # Quantized transformer checkpoints (this repo) | |
| This repo adds pre-quantized diffusion transformer checkpoints for black-forest-labs/FLUX.1-dev, built with torchao | |
| dynamic activation quantization from the dense bf16 transformer. The official model card above | |
| is unchanged from the source repo. | |
| Files: | |
| - FLUX.1-dev-INT8.pt (15.2 GB) | |
| - FLUX.1-dev-FP8.pt (11.9 GB) | |
| Details: | |
| - int8: Int8DynamicActivationInt8WeightConfig (per-token activation, per-channel weight, torch._int_mm). | |
| - fp8: Float8DynamicActivationFloat8WeightConfig with PerRow granularity (e4m3, torch._scaled_mm). | |
| The loader must floor the dynamic activation scale (activation_value_lb=1e-12 on torchao 0.13+) | |
| so all-zero activation token rows cannot produce a zero scale. | |
| - Loading a checkpoint is bit-identical to quantizing the dense bf16 transformer on the fly; | |
| the checkpoint skips the dense load and quantize step. | |
| - Validated against same-seed dense bf16 renders (SSIM, LPIPS-vgg, CLIP delta, non-finite and | |
| black-frame checks) on torch 2.12.1 and torchao 0.17. | |
| Note: Derived from black-forest-labs/FLUX.1-dev and distributed under the | |
| [FLUX.1-dev Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md). | |
| The weights are modified only by the quantization described above. Not an official Black Forest Labs | |
| product and not endorsed by Black Forest Labs. | |
| ## Samples | |
| Prompt: "cute sloth typing on a computer" (1024x1024, family default steps/guidance, seeds 0-2). | |
| **int8** | |
| <img src="samples/int8_1.png" width="260"> <img src="samples/int8_2.png" width="260"> <img src="samples/int8_3.png" width="260"> | |
| **fp8** | |
| <img src="samples/fp8_1.png" width="260"> <img src="samples/fp8_2.png" width="260"> <img src="samples/fp8_3.png" width="260"> | |