{"templateId":"markdown","sharedDataIds":{"sidebar":"sidebar-sidebars.yaml"},"props":{"metadata":{"markdoc":{"tagList":["tabs","tab"]},"type":"markdown"},"seo":{"title":"Self-host Fibo 2 Turbo","description":"Generate and edit images and video with Bria's Fibo models through a REST API, Python and TypeScript SDKs, MCP server and agent skills. Licensed training data, controllable output, provenance on every result.","siteUrl":"https://docs.bria.ai","image":"/assets/bria-social-card.5f3c59395e7b5efa776984c64ef9cb0956b1d651f45b7ebf9502122a66054f35.db81178d.png","llmstxt":{"hide":false,"title":"Bria API documentation","description":"Bria's developer platform: controllable, commercially safe visual generative AI (images and video) as a REST API, Python and TypeScript SDKs, MCP server and agent skills.","details":{"path":"_llmstxt-details.md"},"sections":[{"title":"Getting started","description":"First call, authentication, async jobs and webhooks, rate limits, inputs.","includeFiles":["index.md","whats-new/fibo-2.md","whats-new/rmbg-3.md","getting-started/quickstart.md","getting-started/authentication.md","getting-started/async-requests.md","status.yaml","getting-started/rate-limits-and-errors.md","getting-started/working-with-images.md","getting-started/asset-retention.md"]},{"title":"Integrate","description":"Python SDK, TypeScript SDK, MCP server, agent skills, and machine-readable docs for agents.","includeFiles":["integration-methods/python-sdk.md","integration-methods/typescript-sdk.md","MCP-authentication.md","integration-methods/bria-skill.md","integration-methods/for-ai-agents.md"]},{"title":"Concepts","description":"Platform map, VGL and the Fibo models, safety, best practices.","includeFiles":["products-overview.md","VGL.md","safety.md","best-practices-overview.md","image-generation-best-practices.md","image-editing-best-practices.md","product-shots-best-practices.md"]},{"title":"Image Generation","description":"Generate images from text, reference images or structured (VGL) prompts with Fibo 2.","includeFiles":["image-generation-overview.md","image-generation.yaml"]},{"title":"Image Editing","description":"Instruction-based editing plus specialized endpoints for backgrounds, erasing, fill, expansion, upscaling and style.","includeFiles":["image-editing-overview.md","image-editing.yaml"]},{"title":"Product Shot Editing","description":"Cutouts, packshots, shadows, lifestyle scenes, product integration, holding, virtual try-on, automotive.","includeFiles":["product-shot-overview.md","product-shot-editing.yaml"]},{"title":"Video Editing","description":"Background removal (REST or real-time streaming), erasing, upscaling and masks for video; local video upload.","includeFiles":["video-editing-overview.md","local-video-upload-service.md","streaming-rmbg.md","video-editing.yaml"]},{"title":"Ads","description":"Finished ads as input. Ad Delayer turns one into editable layers (the guide holds the layer document contract); Ad Resize produces it at other sizes with the layout redone.","includeFiles":["ads-overview.md","ads.yaml"]},{"title":"Trust and provenance","description":"Public verification of Bria provenance, and attribution of outputs to licensed training data.","includeFiles":["trust-and-provenance-overview.md","visual-verification-overview.md","visual-verification.yaml","enterprise/attribution.md","bria-attribution-service.yaml"]},{"title":"Self-hosting","description":"Run licensed Bria models on your own GPUs. Buy a per-model license, install with Bria Studio or the Python library, run, and handle license errors.","includeFiles":["self-hosted/quickstart.md","self-hosted/overview.md","self-hosted/best-practices.md","self-hosted/fibo-2.md","self-hosted/fibo-2-turbo.md","self-hosted/rmbg-2.md","self-hosted/rmbg-3.md"]},{"title":"Enterprise","description":"Run Bria in your own cloud or on-premises.","includeFiles":["enterprise/deployment-options.md"]}],"excludeFiles":["_llmstxt-details.md","README.md"]}},"dynamicMarkdocComponents":[],"compilationErrors":[],"ast":{"$$mdtype":"Tag","name":"article","attributes":{},"children":[{"$$mdtype":"Tag","name":"Heading","attributes":{"level":1,"id":"self-host-fibo-2-turbo","__idx":0},"children":["Self-host Fibo 2 Turbo"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Run Fibo 2 Turbo image editing on your own hardware with a self-hosted license. Fibo 2 Turbo edits images only: give it 1 to 4 images and an instruction, and it returns one edited image. This guide installs the model, downloads its weights from Bria, and runs a first edit."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"fibo-2-turbo-or-fibo-2","__idx":1},"children":["Fibo 2 Turbo or Fibo 2?"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Fibo 2 Turbo is Fibo 2's edit model, distilled to run in 4 steps without guidance. An edit of one image takes about 6 seconds on an NVIDIA L40S (four images: about 18 seconds). It does not generate an image from a prompt alone. To generate, use ",{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/self-hosted/fibo-2"},"children":["Fibo 2"]},"."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Each model is licensed on its own: a Fibo 2 license does not cover Fibo 2 Turbo, and a Fibo 2 Turbo license does not cover Fibo 2. You do not need a Fibo 2 license to run Fibo 2 Turbo, although its package installs the ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["fibo-2"]}," package."]},{"$$mdtype":"Tag","name":"div","attributes":{"className":"md-table-wrapper"},"children":[{"$$mdtype":"Tag","name":"table","attributes":{"className":"md"},"children":[{"$$mdtype":"Tag","name":"thead","attributes":{},"children":[{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"th","attributes":{"data-label":""},"children":[]},{"$$mdtype":"Tag","name":"th","attributes":{"data-label":"Fibo 2 Turbo"},"children":["Fibo 2 Turbo"]},{"$$mdtype":"Tag","name":"th","attributes":{"data-label":"Fibo 2"},"children":[{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/self-hosted/fibo-2"},"children":["Fibo 2"]}]}]}]},{"$$mdtype":"Tag","name":"tbody","attributes":{},"children":[{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":["What it does"]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["Edits 1 to 4 images"]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["Generates and edits images"]}]},{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":["GPU memory"]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["32 GB or more"]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["40 GB"]}]},{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":["Python"]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["3.11 or 3.12"]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":["3.11 or 3.12"]}]},{"$$mdtype":"Tag","name":"tr","attributes":{},"children":[{"$$mdtype":"Tag","name":"td","attributes":{},"children":["LLM setting for free-form instructions"]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["FIBO_2_TURBO_VGL_LLM"]}]},{"$$mdtype":"Tag","name":"td","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["FIBO_2_VGL_LLM"]}]}]}]}]}]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"requirements","__idx":2},"children":["Requirements"]},{"$$mdtype":"Tag","name":"ul","attributes":{},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":["An active ",{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["Fibo 2 Turbo"]}," self-hosted license (",{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"https://platform.bria.ai/licensing/pricing?model=fibo-2-turbo"},"children":["pricing"]},")"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["One of your organization's ",{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/getting-started/authentication"},"children":["API keys"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["A machine with an NVIDIA GPU with 32 GB of memory or more, Python 3.11 or 3.12, and about 26 GB of disk for the weights"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["For free-form instructions only: an LLM that turns them into a structured ",{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/vgl"},"children":["VGL"]}," prompt, on your own provider account. A VGL that carries an ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["edit_instruction"]}," needs no LLM (see ",{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"#llm-for-free-form-instructions"},"children":["LLM for free-form instructions"]},")"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["For the manual install: ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["curl"]}," and ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["jq"]},", and network access to the Bria Engine, AWS CodeArtifact and Bria's weights CDN (no Hugging Face account)"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["On H100 and H200 GPUs only: network access to ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["huggingface.co"]}," when the model starts, for its FlashAttention-3 kernel (no account needed)"]}]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"1-get-a-license","__idx":3},"children":["1. Get a license"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Buy a Fibo 2 Turbo license on the ",{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"https://platform.bria.ai/licensing/pricing?model=fibo-2-turbo"},"children":["pricing page"]},". You manage it, and see the installation steps, on the ",{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"https://platform.bria.ai/organization-management/licensing"},"children":["Licenses tab"]}," in the Console."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"2-install","__idx":4},"children":["2. Install"]},{"$$mdtype":"Tag","name":"Tabs","attributes":{"size":"medium"},"children":[{"$$mdtype":"Tag","name":"TabItemFragment","attributes":{"label":"Bria Studio (recommended)","disable":false},"children":[{"$$mdtype":"Tag","name":"p","attributes":{},"children":[{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/self-hosted/quickstart"},"children":["Bria Studio"]}," installs the package, downloads the weights, and runs a test for you. It needs Node.js 18 or newer, ",{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"https://docs.astral.sh/uv/"},"children":["uv"]}," and an NVIDIA GPU."]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"bash","header":{"controls":{"copy":{}}},"source":"npx @bria-ai/studio\n","lang":"bash"},"children":[]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Choose ",{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["Set up a Bria model"]},", then pick ",{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["FIBO 2 Turbo (edit)"]}," when Studio lists your licensed models. It installs ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["fibo-2-turbo"]}," into a Python 3.12 virtual environment at ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["~/.bria/venvs/fibo-2-turbo"]},", downloads the weights, and edits a sample photo to confirm the setup. The test edit uses a VGL that carries the edit instruction, so it needs no LLM."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Fibo 2 Turbo needs Studio 0.6.0 or newer. If Studio does not list it, run ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["npx @bria-ai/studio@latest"]},"."]}]},{"$$mdtype":"Tag","name":"TabItemFragment","attributes":{"label":"Manual (Docker, CI)","disable":false},"children":[{"$$mdtype":"Tag","name":"p","attributes":{},"children":["In a new virtual environment, install PyTorch for CUDA 12.8 first, then exchange your API key for a short-lived registry credential and install the package:"]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"bash","header":{"controls":{"copy":{}}},"source":"export BRIA_API_TOKEN=\"<your-bria-api-token>\"\n\n# Python 3.12, or 3.11 where the machine has no 3.12\nPYTHON=$(command -v python3.12 || command -v python3.11 || echo python3.12)\n\"$PYTHON\" -m venv .venv && . .venv/bin/activate\n\n# PyTorch for CUDA 12.8 (NVIDIA drivers before 580; PyPI's default build needs CUDA 13)\npip install --require-virtualenv \"torch==2.11.0+cu128\" \"torchvision==0.26.0+cu128\" \\\n  --index-url https://download.pytorch.org/whl/cu128 --extra-index-url https://pypi.org/simple\n\nCA=$(curl -s \"https://engine.prod.bria-api.com/v2/outpost/access/code_artifact?repository=bria-fibo-2-turbo\" \\\n      -H \"api_token: $BRIA_API_TOKEN\" | jq -r '.result.authorization_token')\n\npip install --require-virtualenv --upgrade \"fibo-2-turbo\" \\\n  --extra-index-url \"https://aws:$CA@bria-300465780738.d.codeartifact.us-east-1.amazonaws.com/pypi/bria-fibo-2-turbo/simple/\"\n","lang":"bash"},"children":[]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["The ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["bria-fibo-2-turbo"]}," repository also supplies the ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["fibo-2"]}," package that Fibo 2 Turbo runs on, and the build of ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["diffusers"]}," that ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["fibo-2"]}," needs. Everything else comes from PyPI."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Both installs carry pip's ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["--require-virtualenv"]},": if the virtual environment could not be created, they stop instead of installing into the machine's own Python. Drop the flag to install without a virtual environment, as the Dockerfile in the RMBG 2.0 guide does."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Without the PyTorch line, pip installs PyTorch's default build, which needs an NVIDIA driver 580 or newer. On an older driver ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["setup()"]}," fails with ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["torch.cuda.is_available() is False"]},". If your driver is 580 or newer, you can skip that line."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Weights download on first load (",{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"#3-run-it"},"children":["step 3"]},"). In Docker, start from ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["python:3.12-slim"]},", install the same way (see the ",{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/self-hosted/rmbg-2#2-install"},"children":["RMBG 2.0 Dockerfile"]},", with ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["bria-fibo-2-turbo"]}," and ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["fibo-2-turbo"]},"), and mount ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["~/.bria"]}," to cache the weights."]}]}]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":3,"id":"llm-for-free-form-instructions","__idx":5},"children":["LLM for free-form instructions"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["A VGL that carries an ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["edit_instruction"]}," needs no LLM. A free-form instruction (",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["prompt"]},") goes to an LLM on your own account, with the images, and the LLM writes the ",{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/vgl"},"children":["VGL"]}," of the edit. Set ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["FIBO_2_TURBO_VGL_LLM"]}," to any model name ",{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"https://docs.litellm.ai/docs/providers"},"children":["litellm"]}," supports, and set that provider's credentials. If ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["FIBO_2_TURBO_VGL_LLM"]}," is not set, Fibo 2 Turbo uses Gemini 3.5 Flash-Lite: on Google AI Studio when ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["GEMINI_API_KEY"]}," or ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["GOOGLE_API_KEY"]}," is set, otherwise on Vertex AI with your Vertex AI credentials."]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"bash","header":{"controls":{"copy":{}}},"source":"# For example, OpenAI:\nexport FIBO_2_TURBO_VGL_LLM=\"openai/gpt-5.4\"\nexport OPENAI_API_KEY=\"<your-openai-api-key>\"\n","lang":"bash"},"children":[]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Fibo 2 Turbo does not read Fibo 2's ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["FIBO_2_VGL_LLM"]},", so a Fibo 2 install on the same machine does not change it."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["setup()"]}," checks the LLM setting before it downloads the weights. If ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["FIBO_2_TURBO_VGL_LLM"]}," is set, but litellm does not know it or its provider's credentials are missing, ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["setup()"]}," stops with an error. The error names the missing variables, never their values. If no LLM is set up at all, ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["setup()"]}," continues and logs a warning: a request with a ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["vgl"]}," works, and a request with a ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["prompt"]}," stops with an error."]},{"$$mdtype":"Tag","name":"ul","attributes":{},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["The LLM must read images."]}," Every request is an edit, so the LLM gets the images."]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["Quality."]}," Bria tuned the VGL prompts on Gemini 3.5 Flash-Lite. Other LLMs write different VGLs, so the edits can be different."]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["Models that do not work yet."]}," GPT-4o fails on every request with a ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["prompt"]},": use GPT-4.1 or a newer OpenAI model. Gemini through a proxy (for example ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["openrouter/google/…"]},") can fail on edits: leave ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["FIBO_2_TURBO_VGL_LLM"]}," unset, or use ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["gemini/…"]}," or ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["vertex_ai/…"]},"."]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["Cost."]}," You pay your provider for the LLM calls. The LLM does not change the usage that Bria counts."]}]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"3-run-it","__idx":6},"children":["3. Run it"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Run from the environment the model is installed in. If you used Studio, activate the venv it created:"]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"bash","header":{"controls":{"copy":{}}},"source":"source ~/.bria/venvs/fibo-2-turbo/bin/activate\n","lang":"bash"},"children":[]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Then load the model with your API key and edit an image. On first load ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["setup()"]}," checks your license and downloads the weights (25.5 GB) to ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["~/.bria/models"]},"; later runs reuse them. On an AWS server with an NVIDIA L40S, the download took about 3.5 minutes. Your time depends on your network."]},{"$$mdtype":"Tag","name":"CodeBlock","attributes":{"data-language":"python","header":{"controls":{"copy":{}}},"source":"import os\nfrom io import BytesIO\nfrom urllib.request import urlopen\n\nfrom PIL import Image\nfrom fibo_2_turbo import Fibo2Turbo, Fibo2TurboConfig, Fibo2TurboInput\n\n# Reads BRIA_API_TOKEN; checks the license and downloads ~26 GB of weights on first load.\npipe = Fibo2Turbo(config=Fibo2TurboConfig(api_token=os.environ[\"BRIA_API_TOKEN\"]))\npipe.setup()\n\n# Fibo 2 Turbo edits images: one to four of them, loaded with PIL\nurl = \"https://bria-test-images.s3.us-east-1.amazonaws.com/strawberry.jpg\"\nphoto = Image.open(BytesIO(urlopen(url).read()))\n\n# A structured prompt (VGL) that carries the edit instruction needs no LLM\nvgl = '{\"edit_instruction\": \"Make the strawberry blue\"}'\nresult = pipe.execute(Fibo2TurboInput(images=[photo], vgl=vgl, seed=42))\nresult.image.save(\"edited.png\")\n\n# A free-form instruction needs an LLM (see \"LLM for free-form instructions\")\n# result = pipe.execute(Fibo2TurboInput(images=[photo], prompt=\"Make the strawberry blue\", seed=42))\n\npipe.cleanup()  # free the GPU when you are done\n","lang":"python"},"children":[]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["Fibo2TurboInput"]}," takes:"]},{"$$mdtype":"Tag","name":"ul","attributes":{},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["images"]},": 1 to 4 PIL images. The instruction can refer to them as ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["<image_1>"]},", ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["<image_2>"]}," and so on, in this order. Any image mode works (RGBA, palette, CMYK); the alpha channel is not used."]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["The instruction: a free-form ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["prompt"]}," that your LLM turns into VGL, or a ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["vgl"]}," that carries an ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["edit_instruction"]},". A ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["vgl"]}," sent with a ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["prompt"]}," is the first image's complete VGL, kept as the baseline of the edit."]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["Optional ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["seed"]},", and the size: ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["width"]}," and ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["height"]},", or ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["aspect_ratio"]}," for an edit of two or more images. Without a size, the result is about one megapixel, in the first image's shape."]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["Optional ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["mask"]},": the region to edit, white on black. One image only, at that image's size. A masked edit keeps the image's size and its pixels outside the mask."]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Fibo 2's generation fields, such as ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["style"]}," and ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["negative_prompt"]},", are refused. The result carries ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["image"]},", the edited image, and ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["vgl"]},", the VGL the model read: send it back to reproduce or adjust the edit."]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Inputs and outputs stay on your machine — only a small ",{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/enterprise/attribution"},"children":["attribution"]}," vector is sent to Bria."]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"errors-and-troubleshooting","__idx":7},"children":["Errors and troubleshooting"]},{"$$mdtype":"Tag","name":"details","attributes":{},"children":[{"$$mdtype":"Tag","name":"summary","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["No license for FIBO 2 Turbo"]}]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Your account holds no active Fibo 2 Turbo license, so the install stops before anything downloads. A Fibo 2 license does not cover Fibo 2 Turbo. Buy or renew it on the ",{"$$mdtype":"Tag","name":"a","attributes":{"href":"https://platform.bria.ai/organization-management/licensing"},"children":["Licenses tab"]},"."]}]},{"$$mdtype":"Tag","name":"details","attributes":{},"children":[{"$$mdtype":"Tag","name":"summary","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["LicenseError"]}," when the model starts"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Your account holds no active Fibo 2 Turbo license, or the license ended. Open the ",{"$$mdtype":"Tag","name":"a","attributes":{"href":"https://platform.bria.ai/organization-management/licensing"},"children":["Licenses tab"]}," — the error links straight to it. A card retry (",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["past_due"]},") stays active."]}]},{"$$mdtype":"Tag","name":"details","attributes":{},"children":[{"$$mdtype":"Tag","name":"summary","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["The model won't load and asks for an API token"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["No ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["BRIA_API_TOKEN"]}," is set. Set it (or ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["FIBO_2_TURBO_API_TOKEN"]},"), or pass ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["Fibo2TurboConfig(api_token=\"...\")"]},"."]}]},{"$$mdtype":"Tag","name":"details","attributes":{},"children":[{"$$mdtype":"Tag","name":"summary","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["FIBO 2 Turbo edits images: send 1 to 4 'images'"]}]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["The request has no image. Fibo 2 Turbo edits images only. To generate an image from a prompt, use ",{"$$mdtype":"Tag","name":"a","attributes":{"href":"/self-hosted/fibo-2"},"children":["Fibo 2"]},", which has its own license."]}]},{"$$mdtype":"Tag","name":"details","attributes":{},"children":[{"$$mdtype":"Tag","name":"summary","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["A free-form instruction stops and asks for an LLM"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["No LLM is set up for the instruction. Set ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["FIBO_2_TURBO_VGL_LLM"]}," and its provider's credentials, or ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["GEMINI_API_KEY"]},", or your Vertex AI credentials (see ",{"$$mdtype":"Tag","name":"a","attributes":{"href":"#llm-for-free-form-instructions"},"children":["LLM for free-form instructions"]},"). ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["FIBO_2_VGL_LLM"]}," is not read. Or send a ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["vgl"]}," that carries an ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["edit_instruction"]},", which needs no LLM."]}]},{"$$mdtype":"Tag","name":"details","attributes":{},"children":[{"$$mdtype":"Tag","name":"summary","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["torch.cuda.is_available() is False"]}," during ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["setup()"]}]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["The installed PyTorch doesn't match your NVIDIA driver. pip's default PyTorch needs driver 580 or newer. Install the CUDA 12.8 build first, as in ",{"$$mdtype":"Tag","name":"a","attributes":{"href":"#2-install"},"children":["step 2"]},"."]}]},{"$$mdtype":"Tag","name":"details","attributes":{},"children":[{"$$mdtype":"Tag","name":"summary","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["CUDA out of memory"]}," during ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["setup()"]}," or the first edit"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Fibo 2 Turbo needs a GPU with 32 GB of memory or more. On an NVIDIA L40S, the process used up to 30,901 MiB."]}]},{"$$mdtype":"Tag","name":"details","attributes":{},"children":[{"$$mdtype":"Tag","name":"summary","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":[{"$$mdtype":"Tag","name":"code","attributes":{},"children":["WeightsError"]}," during download"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["The download was interrupted. Run again — it resumes where it stopped."]}]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":2,"id":"usage-and-billing","__idx":8},"children":["Usage and billing"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Each edit is counted against your Fibo 2 Turbo license, not a Fibo 2 license, and shown in ",{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["Usage & billing"]}," in the Console, tagged as self-hosted. See ",{"$$mdtype":"Tag","name":"MarkdownLink","attributes":{"href":"/self-hosted/overview#licensing-and-usage"},"children":["Self-hosted models"]}," for how licensing and billing work across models."]}]},"headings":[{"value":"Self-host Fibo 2 Turbo","id":"self-host-fibo-2-turbo","depth":1},{"value":"Fibo 2 Turbo or Fibo 2?","id":"fibo-2-turbo-or-fibo-2","depth":2},{"value":"Requirements","id":"requirements","depth":2},{"value":"1. Get a license","id":"1-get-a-license","depth":2},{"value":"2. Install","id":"2-install","depth":2},{"value":"LLM for free-form instructions","id":"llm-for-free-form-instructions","depth":3},{"value":"3. Run it","id":"3-run-it","depth":2},{"value":"Errors and troubleshooting","id":"errors-and-troubleshooting","depth":2},{"value":"Usage and billing","id":"usage-and-billing","depth":2}],"frontmatter":{"title":"Self-host Fibo 2 Turbo","description":"Run Bria's Fibo 2 Turbo image editing on your own GPUs with a self-hosted license. Install with Bria Studio or manually (Docker, CI), run a first edit, and handle license errors.","seo":{"title":"Self-host Fibo 2 Turbo"}},"lastModified":"2026-11-22T12:59:36.000Z","pagePropGetterError":{"message":"","name":""}},"slug":"/self-hosted/fibo-2-turbo","userData":{"isAuthenticated":false,"teams":["anonymous"]},"isPublic":true}