Welcome FLUX.3 Image Klein in Diffusers
本文为原文前 6,000 字符的节选翻译，完整内容请查看原文。
Welcome FLUX.3 Image Klein in Diffusers
欢迎使用 Diffusers 中的 FLUX.3 Image Klein：这是来自 Black Forest Labs 的最新开源图像生成模型。
Back to Articles Welcome FLUX.3 Image Klein in Diffusers: The latest open image generation model from Black Forest Labs Published October 15, 2026 Update on GitHub Upvote 23 +17 Aritra Roy Gosthipaty ariG23498 Follow Sayak Paul sayakpaul Follow Linoy Tsaban linoyts Follow Black Forest Labs
FLUX.3 Image Klein 现已发布，并且从第一天起就支持在 Diffusers 中运行。该模型集成了文本生成图像和多参考图像生成图像功能，并新增了布局控制特性。你可以在提示词中写入边界框，以指定图像各部分的放置位置，或移动参考图像中的特定部分。
FLUX.3 Image Klein is here, and it runs in Diffusers from day one. One model does text-to-image and multi-reference image-to-image, and it adds something new, the layout control. You write bounding boxes into the prompt to say where each part of the image should go, or which parts of a reference image to move.
FLUX.3 Image Klein 系列包含两个开源检查点：
Both open checkpoints are in the FLUX.3 Image Klein collection:
| 检查点 (Checkpoint) | 说明 (What it is) | 默认设置 (Defaults) |
|---|---|---|
| black-forest-labs/flux-3-image-klein | 时间步蒸馏，用于快速推理 | 16 步，无 CFG |
| black-forest-labs/flux-3-image-klein-base | 基础模型 | 50 步，带 CFG |
| Checkpoint | What it is | Defaults | | :--- | :--- | :--- | | black-forest-labs/flux-3-image-klein | Time step distilled, for fast inference | 16 steps, no CFG | | black-forest-labs/flux-3-image-klein-base | Base model | 50 steps, CFG |
你可以立即前往 Hugging Face Space 生成图像！
You can head on to the Hugging Face space and generate some images right now!
简而言之：一个模型即可实现文本生成图像、多参考图像生成图像以及边界框布局控制。蒸馏检查点在 H100 上约 2 秒即可生成 1024 × 1024 的图像。NVFP4 和 FP8 权重可通过 from_single_file 加载，适用于较小的 GPU。此外还提供用于文本生成图像和图像编辑的 LoRA 训练脚本。该模型以模块化 Diffusers 流水线形式发布，因此你可以移除或添加自己的模块。
TL;DR One model for text-to-image, multi-reference image-to-image, and bounding-box layout control. The distilled checkpoint makes a 1024 × 1024 image in about 2 seconds on an H100. NVFP4 and FP8 weights load with from_single_file, for smaller GPUs. LoRA training scripts for both text-to-image and image editing. Ships as a Modular Diffusers pipeline, so you can pop blocks out or add your own.
入门指南：安装最新的 diffusers 和 transformers（用于 Qwen3-VL 文本编码器）：pip install -U diffusers transformers。加载蒸馏检查点并生成图像：
Getting started Install the latest diffusers and transformers (for the Qwen3-VL text encoder): pip install -U diffusers transformers Load the distilled checkpoint and generate an image:
import torch
from diffusers import ModularPipeline
pipe = ModularPipeline.from_pretrained("black-forest-labs/flux-3-image-klein")
pipe.load_components(dtype=torch.bfloat16)
pipe.to("cuda")
pipe(prompt="a red fox", output="images")[0].save("fox.png")import torch from diffusers import ModularPipeline pipe = ModularPipeline.from_pretrained(“black-forest-labs/flux-3-image-klein”) pipe.load_components(dtype=torch.bfloat16) pipe.to(“cuda”) pipe(prompt=“a red fox”, output=“images”)[0].save(“fox.png”)