# FLUX.2 [klein] 9B Base > FLUX.2 [klein] 9B Base is Black Forest Labs' 9-billion-parameter rectified flow transformer for text to image and multi-reference editing, trained without step or guidance distillation so it keeps full flexibility for fine-tuning and LoRA work. Weights are under the FLUX Non-Commercial License and need about 29 GB of VRAM locally. On Kenerate AI it runs in the browser for 4.5 credits per image, with up to 3 reference images for edits. URL: https://kenerateai.com/models/black-forest-labs/flux-2-klein-base-9b Publisher: Kenerate AI (https://kenerateai.com) Last updated: 18 October 2026 ## Key facts - Official name: FLUX.2 [klein] 9B Base - Hugging Face ID: black-forest-labs/FLUX.2-klein-base-9B - Maker: Black Forest Labs - Size: 9B parameters · BF16 - Distillation: None (base model) - Licence: FLUX Non-Commercial - Local VRAM: ≈29 GB (RTX 4090 and up) - On Kenerate: 4.5 credits · edit 6.3 - References: Up to 3 - Max size on Kenerate: 1536×1536 ## Steps 1. Open the model — Go to /app/image and pick Flux 2 Klein Base 9B (the button on this page selects it for you). Sign in free to get started. 2. Write the prompt — Describe medium, subject, setting, light and camera in plain sentences. Put exact on-image words in quotes. 3. Pick a size and seed — Choose one of 8 sizes up to 1536×1536 and fix the seed when you want to compare prompt changes. 4. Edit with references — Upload up to 3 images and say what changes and what stays — an edit costs 6.3 credits. ## In depth ### Base vs distilled: which FLUX.2 [klein] 9B to use Black Forest Labs ships the 9B [klein] model twice: a distilled version tuned for speed, and this undistilled Base, trained without step or guidance distillation [1]. ComfyUI provides separate workflows for each [2]. - Base 9B — full guidance, more steps; the starting point for fine-tunes, LoRAs and research. - Distilled 9B — far fewer steps, for fast generation and editing. - 4B [klein] — smaller and Apache 2.0; Flux 2 Klein (4B) is on Kenerate's free plan. ### Running it yourself vs in the browser Locally, the BF16 weights need about 29 GB of VRAM (RTX 4090 class and up) [1]; ComfyUI Wiki lists an FP8 file of about 9.5 GB for smaller cards [3]. On Kenerate there is nothing to install: 4.5 credits per image, 8 sizes up to 1536×1536, and up to 3 references for edits. References: [1] black-forest-labs/FLUX.2-klein-base-9B — Hugging Face model card: https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B [2] FLUX.2 [klein] tutorial — ComfyUI docs: https://docs.comfy.org/tutorials/flux/flux-2-klein [3] FLUX.2 Klein 9B — ComfyUI Wiki: https://comfyui-wiki.com/en/models/flux/flux-2-klein [4] Flux (text-to-image model) — Wikipedia: https://en.wikipedia.org/wiki/Flux_(text-to-image_model) ## FAQ Q: What is FLUX.2 [klein] 9B Base? A: FLUX.2 [klein] 9B Base is a 9-billion-parameter rectified flow transformer from Black Forest Labs, published on Hugging Face as black-forest-labs/FLUX.2-klein-base-9B. It generates images from text and edits them with multiple references. “Base” means it was trained without step or guidance distillation, which keeps it flexible for fine-tuning, LoRA training and research. Q: What is the difference between FLUX.2 klein 9B Base and FLUX.2 klein 9B? A: The base model is undistilled: it keeps the full sampling process and classifier-free guidance, so it needs more steps (the model card's example uses 50) but is the better starting point for fine-tunes and LoRAs. The distilled FLUX.2 [klein] 9B is tuned for speed and needs far fewer steps. Black Forest Labs says the base suits work “where control matters more than speed”. Q: Can I use FLUX.2 klein 9B Base online without a GPU? A: Yes. Kenerate AI runs it in the browser as Flux 2 Klein Base 9B, with no download or setup. It costs 4.5 credits per image and 6.3 per edit, takes up to 3 reference images and offers 8 sizes up to 1536×1536. Running the weights yourself needs about 29 GB of VRAM, per the model card. Q: Is FLUX.2 klein 9B Base free? A: The weights are free to download from Hugging Face after you accept the licence, but you need your own high-VRAM GPU. On Kenerate the 9B Base is a paid model (4.5 credits per image from a one-time credit pack, no subscription). The free plan includes Flux 2 Klein (4B) and Flux 2 Dev if you want free FLUX.2 images. Q: What licence does FLUX.2 klein 9B Base use? A: The 9B weights are released under the FLUX Non-Commercial License, according to the Hugging Face model card. The 4B [klein] models are Apache 2.0. Read Black Forest Labs' licence before using a self-hosted 9B model commercially; images you generate on Kenerate follow Kenerate's terms of service. Q: What is black-forest-labs/FLUX.2-klein-base-9B-fp8? A: It refers to an 8-bit (FP8) copy of the same 9B Base weights, which ComfyUI lists for its FLUX.2 [klein] workflows. ComfyUI Wiki puts the full checkpoint at about 18.9 GB and the FP8 file at about 9.5 GB, so FP8 fits smaller GPUs at some cost in precision. On Kenerate you don't choose a file — the hosted model runs for you. Q: Can FLUX.2 klein 9B Base edit images? A: Yes. The model card lists multi-reference editing. On Kenerate, upload up to 3 reference images to Flux 2 Klein Base 9B and describe the change and what must stay, for example “same pose, swap the background for a beach”. Each edit costs 6.3 credits. Q: How good is FLUX.2 klein 9B Base at text in images? A: Mixed in our test. Large Latin lettering worked — “LISBOA” on a travel poster was spelled right first try — but small text and Japanese signage came out as gibberish. For posters with lots of text, try GPT Image 2 or Qwen Image on Kenerate instead. Q: What settings does the model card recommend? A: The Diffusers example on the Hugging Face card generates at 1024×1024 with 50 inference steps and a guidance scale of 4.0, and suggests CPU offload to save VRAM. Wiro's API example uses 30 steps and scale 4. On Kenerate the steps and guidance are set for you; you choose the prompt, size and seed. ## Related pages - Flux 2 (all versions): https://kenerateai.com/model/flux-2 - Z Image: https://kenerateai.com/model/z-image - Chroma: https://kenerateai.com/model/chroma - All models: https://kenerateai.com/model ## Sources - black-forest-labs/FLUX.2-klein-base-9B — Hugging Face model card: https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B - FLUX.2 [klein] tutorial — ComfyUI docs: https://docs.comfy.org/tutorials/flux/flux-2-klein - FLUX.2 Klein 9B — ComfyUI Wiki: https://comfyui-wiki.com/en/models/flux/flux-2-klein - Flux (text-to-image model) — Wikipedia: https://en.wikipedia.org/wiki/Flux_(text-to-image_model)