Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.bfl.ml/llms.txt

Use this file to discover all available pages before exploring further.

Public Beta — LoRA inference endpoints are in public beta. Pricing, parameters, and endpoint names may change before general availability.
Train a LoRA once with the tools of your choice (AI-Toolkit, Diffusers, …), upload it to the BFL Dashboard — where they’re surfaced as Finetunes — then serve inference through a managed endpoint. No GPUs to provision, same polling workflow as the rest of the FLUX.2 API.
New to training? Start with the FLUX.2 [klein] Training guide and the step-by-step training example, then come back here to serve your LoRA.

​
How It Works

1

Train a LoRA

Train a LoRA locally against a FLUX.2 [klein] Base model using AI-Toolkit or Diffusers. The Dashboard upload dialog accepts .safetensors checkpoints.
2

Upload it to the Dashboard

In the Dashboard, go to Customization → Finetunes and click + Add Finetune. Pick the matching base model, give it a name (lowercase letters, digits, hyphens, and underscores only), optionally set a trigger phrase, and drop in the checkpoint. The name you pick is your finetune_id.
3

Call the fine-tuned endpoint

POST to the {base_model}-finetuned endpoint with your finetune_id, then poll the returned polling_url until status is Ready.

​
Available Endpoints

Each supported base model has a corresponding -finetuned endpoint. The request schema matches the underlying base endpoint, with two added parameters: finetune_id and finetune_strength.
EndpointBase ModelPrecision
/v1/flux-2-klein-4b-finetunedFLUX.2 [klein] 4BFP8
/v1/flux-2-klein-9b-finetunedFLUX.2 [klein] 9BFP8
/v1/flux-2-klein-9b-kv-finetunedFLUX.2 [klein] 9B (KV-cached)FP8
/v1/flux-2-klein-9b-kv-bf16-finetunedFLUX.2 [klein] 9B (KV-cached)BF16
/v1/flux-2-klein-base-4b-finetunedFLUX.2 [klein] Base 4BFP8
/v1/flux-2-klein-base-9b-finetunedFLUX.2 [klein] Base 9BFP8
The endpoint you call must match the base model and precision selected in the Dashboard. FP8 is the default precision. BF16 is currently available only for flux-2-klein-9b-kv and maps to /v1/flux-2-klein-9b-kv-bf16-finetuned.

​
finetune_id format

  • Own LoRA: pass the name you chose in the Dashboard (e.g. my-portrait-lora).
  • LoRA shared with your organization: prefix the owner’s organization ID — {owner_org_id}/{lora_name}.

​
Quick Start

Replace my-portrait-lora with the name of a finetune uploaded to your organization. 
# Submit
RESPONSE=$(curl -s -X POST 'https://api.bfl.ai/v1/flux-2-klein-9b-kv-finetuned' \
  -H "x-key: $BFL_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "prompt": "A portrait of ohwx in a sunlit studio, soft key light",
    "finetune_id": "my-portrait-lora",
    "finetune_strength": 1.0
  }')
POLLING_URL=$(echo "$RESPONSE" | jq -r '.polling_url')

# Poll
while true; do
  RESULT=$(curl -s "$POLLING_URL" -H "x-key: $BFL_API_KEY")
  STATUS=$(echo "$RESULT" | jq -r '.status')
  [ "$STATUS" = "Ready" ] && echo "$RESULT" | jq -r '.result.sample' && break
  [ "$STATUS" = "Error" ] || [ "$STATUS" = "Failed" ] && echo "$RESULT" && break
  sleep 1
done
The async submit-and-poll pattern, response shape, and signed-URL expiry are the same as every other FLUX.2 endpoint. See API Integration for the canonical reference.

​
Request Parameters

The -finetuned endpoint accepts every parameter of its base endpoint, plus these two LoRA-specific fields:
ParameterTypeRequiredDescription
finetune_idstringYesName of an uploaded finetune available to your organization. For finetunes shared with you, prefix with the owner org ID: {owner_org_id}/{name}.
finetune_strengthfloatNoHow strongly the LoRA is applied. Defaults to 1.0. See Tuning finetune_strength below. Include the LoRA’s trigger phrase in prompt if one was set.
For the rest of the request and response schema (prompt, dimensions, input_image_*, seed, output format, polling response), see the base endpoint in the API Reference.

​
Behavior & Limits

  • One LoRA per request. The API takes a single finetune_id; stacking multiple LoRAs is not supported.
  • Base-model match is strict. Calling flux-2-klein-4b-finetuned with a finetune_id uploaded for flux-2-klein-9b will fail — pick the endpoint that matches the finetune’s base model.
  • Rate limits and polling are identical to the base endpoint. See API Integration.

​
Tuning finetune_strength

finetune_strength scales the LoRA’s contribution at inference time.
  • Start at 1.0 — the default, and what the Dashboard’s copy-paste snippet uses.
  • If the LoRA overpowers the prompt (every output looks like your training set regardless of what you ask for), sweep 0.7 → 0.9 with the same seed to find the point where the style/subject is preserved without collapsing variety.
  • Lower values bias the generation back toward the base model.
  • Always include the LoRA’s trigger phrase (if one was set during upload) in the prompt — strength alone won’t activate a phrase-gated LoRA.

​
Using Finetunes in the Playground

Finetunes are also available in the Playground. Open the model picker, expand Finetunes, and pick one of your uploaded finetunes — the Playground auto-routes to the matching -finetuned endpoint.
Playground model picker with Finetunes submenu expanded, showing an uploaded finetune tagged with its base model and a link to manage finetunes

​
Managing Finetunes in the Dashboard

LoRAs are managed under Customization → Finetunes in the Dashboard, where the feature is currently marked BETA. The list view shows columns for Name, Base Model, Source (Owned / Official / Third party), and Actions, with All / Owned / Shared filter tabs. Clicking a row expands an inline detail panel with an auto-generated API example and editable settings.
BFL Dashboard Finetunes list view with All / Owned / Shared tabs and columns for Name, Base Model, Source, Actions

​
Uploading a finetune

Click + Add Finetune in the top-right to open the upload dialog. Fields:
Add Finetune dialog with Name, Base Model, Trigger Phrase, and Checkpoint File fields
FieldNotes
NameBecomes your finetune_id. Validation: Lowercase letters, digits, hyphens, and underscores only.
Base ModelDropdown. Must match the model your LoRA was trained against — this determines which -finetuned endpoint to call.
PrecisionDropdown. FP8 is the default. BF16 is currently available only for flux-2-klein-9b-kv.
Trigger Phrase (optional)Placeholder e.g. TOK, sks, ohwx. A keyword to include in prompts when using this finetune.
Checkpoint File.safetensors file, drag-and-drop or click to select.
Submit with Upload Finetune.

​
Editing a finetune

Expanding a row reveals the detail panel, which contains:
Expanded Finetune detail panel showing the auto-generated curl API example plus editable Base Model, Precision, Trigger Phrase, and organization sharing fields
  • Base Model — dropdown, can be changed post-upload if needed.
  • Precision — dropdown with FP8 and BF16. BF16 can currently be selected only for flux-2-klein-9b-kv.
  • Trigger Phrase — editable, clearable.
  • Share with another Organization — input labelled Organization ID plus a + Grant button to share the finetune with another BFL organization.
  • API Example — an auto-generated curl snippet that pre-fills finetune_id, finetune_strength, and a prompt that uses the trigger phrase if one is set.
Non-owners address the finetune by its fully-qualified ID: {owner_org_id}/{finetune_name}. Organization sharing is targeted by organization ID. Granted finetunes appear under the recipient’s Shared tab.
Billing is always on the caller. Generations are billed to the API key that issues the request, regardless of who owns the finetune. Granting a finetune to another org does not expose the owner to inference costs incurred by callers.

​
Pricing

During public beta, LoRA endpoints are billed at the same rate as their base endpoint at the same resolution. See API Pricing for the current rates.

​
Next Steps

Train a [klein] LoRA

Learn how to train a LoRA against a FLUX.2 [klein] Base model.

Training Example

Step-by-step walkthrough with a real dataset.

API Pricing

Current rates for fine-tuned endpoints.

API Reference

Full request and response schemas.