unsloth/flux.1-schnell-gguf overview

{
  "metadata": {},
  "card_data": {
    "language": [
      "en"
    ],
    "license": "apache-2.0",
    "tags": [
      "text-to-image",
      "image-generation",
      "flux"
    ],
    "base_model": [
      "black-forest-labs/FLUX.1-schnell"
    ],
    "frontmatter": {
      "language": [
        "en"
      ],
      "license": "apache-2.0",
      "tags": [
        "text-to-image",
        "image-generation",
        "flux"
      ],
      "base_model": [
        "black-forest-labs/FLUX.1-schnell"
      ]
    },
    "hero_image_url": "",
    "summary": "1. Cutting-edge output quality and competitive prompt following, matching the performance of closed source alternatives. 2. Trained using latent adversarial diffusion distillation, FLUX.1 [schnell] can generate high-quality images in only 1 to 4 steps. 3. Released under the apache-2.0 licence, the model can be used for personal, scientific, and commercial purposes. # Usage We provide a reference implementation of FLUX.1 [schnell], as well as sampling code, in a dedicated github repository. Developers and creatives looking to build on top of FLUX.1 [schnell] are encouraged to use this as a starting point.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlanguage:\n- en\nlicense: apache-2.0\ntags:\n- text-to-image\n- image-generation\n- flux\nbase_model:\n- black-forest-labs/FLUX.1-schnell\n---\n\n`FLUX.1 [schnell]` is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions.\nFor more information, please read our [blog post](https://blackforestlabs.ai/announcing-black-forest-labs/).\n# Key Features\n1. Cutting-edge output quality and competitive prompt following, matching the performance of closed source alternatives.\n2. Trained using latent adversarial diffusion distillation, `FLUX.1 [schnell]` can generate high-quality images in only 1 to 4 steps.\n3. Released under the `apache-2.0` licence, the model can be used for personal, scientific, and commercial purposes.\n# Usage\nWe provide a reference implementation of `FLUX.1 [schnell]`, as well as sampling code, in a dedicated [github repository](https://github.com/black-forest-labs/flux).\nDevelopers and creatives looking to build on top of `FLUX.1 [schnell]` are encouraged to use this as a starting point.\n## API Endpoints\nThe FLUX.1 models are also available via API from the following sources\n- [bfl.ml](https://docs.bfl.ml/) (currently `FLUX.1 [pro]`)\n- [replicate.com](https://replicate.com/collections/flux)\n- [fal.ai](https://fal.ai/models/fal-ai/flux/schnell)\n- [mystic.ai](https://www.mystic.ai/black-forest-labs/flux1-schnell)\n## ComfyUI\n`FLUX.1 [schnell]` is also available in [Comfy UI](https://github.com/comfyanonymous/ComfyUI) for local inference with a node-based workflow.\n## Diffusers\nTo use `FLUX.1 [schnell]` with the 🧨 diffusers python library, first install or upgrade diffusers\n```shell\npip install -U diffusers\n```\nThen you can use `FluxPipeline` to run the model\n```python\nimport torch\nfrom diffusers import FluxPipeline\npipe = FluxPipeline.from_pretrained(\"black-forest-labs/FLUX.1-schnell\", torch_dtype=torch.bfloat16)\npipe.enable_model_cpu_offload() #save some VRAM by offloading the model to CPU. Remove this if you have enough GPU power\n\nprompt = \"A cat holding a sign that says hello world\"\nimage = pipe(\n    prompt,\n    guidance_scale=0.0,\n    num_inference_steps=4,\n    max_sequence_length=256,\n    generator=torch.Generator(\"cpu\").manual_seed(0)\n).images[0]\nimage.save(\"flux-schnell.png\")\n```\nTo learn more check out the [diffusers](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux) documentation\n\n---\n# Limitations\n- This model is not intended or able to provide factual information.\n- As a statistical model this checkpoint might amplify existing societal biases.\n- The model may fail to generate output that matches the prompts.\n- Prompt following is heavily influenced by the prompting-style.\n\n# Out-of-Scope Use\nThe model and its derivatives may not be used\n\n- In any way that violates any applicable national, federal, state, local or international law or regulation.\n- 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.\n- To generate or disseminate verifiably false information and/or content with the purpose of harming others.\n- To generate or disseminate personal identifiable information that can be used to harm an individual.\n- To harass, abuse, threaten, stalk, or bully individuals or groups of individuals.\n- To create non-consensual nudity or illegal pornographic content.\n- For fully automated decision making that adversely impacts an individual's legal rights or otherwise creates or modifies a binding, enforceable obligation.\n- Generating or facilitating large-scale disinformation campaigns.",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "text-to-image",
    "image-generation",
    "flux",
    "en",
    "base_model:black-forest-labs/FLUX.1-schnell",
    "base_model:quantized:black-forest-labs/FLUX.1-schnell",
    "license:apache-2.0",
    "region:us"
  ],
  "likes": 14,
  "downloads": 1907,
  "gated": false,
  "private": false,
  "last_modified": "2025-06-30T10:56:24.000Z",
  "created_at": "2025-06-30T10:50:31.000Z",
  "pipeline_tag": "text-to-image",
  "library_name": ""
}

{
  "_id": "68626bf794640fe6cf34e3e2",
  "id": "unsloth/FLUX.1-schnell-GGUF",
  "modelId": "unsloth/FLUX.1-schnell-GGUF",
  "sha": "65b3e21589c5dc66402b02a079208201ae9fcfc3",
  "createdAt": "2025-06-30T10:50:31.000Z",
  "lastModified": "2025-06-30T10:56:24.000Z",
  "author": "unsloth",
  "downloads": 1907,
  "likes": 14,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-to-image",
  "library_name": "",
  "siblings_count": 17
}