Generate training-matched FLUX.2 Klein 9B LoRA outputs in ComfyUI through AI Toolkit's pipeline-aligned inference nodes.

Who it's for: creators who want this pipeline in ComfyUI without assembling nodes from scratch. Not for: one-click results with zero tuning — you still choose inputs, prompts, and settings.

Open preloaded workflow on RunComfy

Open preloaded workflow on RunComfy (browser)

Why RunComfy first
- Fewer missing-node surprises — run the graph in a managed environment before you mirror it locally.
- Quick GPU tryout — useful if your local VRAM or install time is the bottleneck.
- Matches the published JSON — the zip follows the same runnable workflow you can open on RunComfy.

When downloading for local ComfyUI makes sense — you want full control over models on disk, batch scripting, or offline runs.

How to use (local ComfyUI)
1. Load inputs (images/video/audio) in the marked loader nodes.
2. Set prompts, resolution, and seeds; start with a short test run.
3. Export from the Save / Write nodes shown in the graph.

Expectations — First run may pull large weights; cloud runs may require a free RunComfy account.

Overview

FLUX.2 Klein 9B LoRA ComfyUI Inference gives you a ready-to-run ComfyUI graph for applying AI Toolkit-trained LoRAs on FLUX.2 Klein 9B with pipeline-level accuracy. Flux2Klein9BPipeline wraps the Klein 9B inference pipeline-Qwen3-8B text encoding, flow-match scheduling, and internal adapter injection-so ComfyUI generation behaves the same way AI Toolkit renders training previews. Adapter loading supports local files in models/loras or direct .safetensors URLs, controlled by lora_path and lora_scale. Because Klein 9B is not guidance-distilled, guidance_scale directly shapes output quality; matching it to your training sample config avoids the most common source of preview mismatch. The workflow outputs standard images through SaveImage for straightforward side-by-side comparison with training previews.

Important nodes:

• Load Pipeline

• SaveImage

• RC FLUX.2

Notes

FLUX.2 Klein 9B LoRA ComfyUI Inference | RunComfy Workflow (Training-Matched Results) — see RunComfy page for the latest node requirements.