AIniverse Get the App

Flux2-Klein-9B-True-V3

================================================================================== ✌️✌️✌️ 0Day Support "**int4_convrot**" quantized format with Comfy-Org, [Flux2-Klein-9B-True-V3-int4_convrot.safetensors](https://huggingface.co/wikeeyang/Flux2-Klein-9B-True-V3/resolve/main/Flux2-Klein-9B-True-V3-int4_convrot.safetensors) 您可以尝试一下全新的 ComfyUI GGUF 模型加载插件 [**smthemex/ComfyUI_Dif_GGUF**](https://github.com/smthemex/ComfyUI_Dif_GGUF),它能适配更多的 GGUF 文件格式,并且将很快集成低显存(4-8GB)显卡的 GGUF 模型块卸载管理能力。 Recommend to try the new GGUF ComfyUI loader plugin, [**smthemex/ComfyUI_Dif_GGUF**](https://github.com/smthemex/ComfyUI_Dif_GGUF), it compatible with more GGUF format, and will add low VRAM (4-8GB) management for GGUF soon. **Provide Int8 version, it's twice as fast as fp8.** Much thanks [@**Milor123**](https://huggingface.co/Milor123) to privide Int8 quantized version [Flux2-Klein-9B-True-V3-INT8-ConvRot.safetensors](https://huggingface.co/wikeeyang/Flux2-Klein-9B-True-V3/blob/main/Flux2-Klein-9B-True-V3-INT8-ConvRot.safetensors), it can load by [ComfyUI-INT8-Fast](https://github.com/BobJohnson24/ComfyUI-INT8-Fast). Also I had to quantized and uploaded the Int8 version of the model, which can be loaded directly with ComfyUI's official node, [Flux2-Klein-9B-True-V3-int8mixedrow.safetensors](https://huggingface.co/wikeeyang/Flux2-Klein-9B-True-V3/blob/main/Flux2-Klein-9B-True-V3-int8mixedrow.safetensors) **The version 3 has significant improvements, basically solving some of the issues present in V1/V2, with noticeable enhancements in aesthetics and composition. See the examples below:** 1. **不同量化精度出图质量对比,量化损失很小。High-quality quantization parameters, the loss is very low.** 2. **与官方及旧版模型对比效果。Comparison with the official and old versions.** 3. **V1 - V3 样例与对比。Examples and Comparisons of V1 - V3.** 4. **仅提示词指令图像编辑。Just use instruct prompt to edit image.** 提示词:给他穿上粗犷的牛仔服外套,敞开着,露出他原来穿的T恤和图案,戴上一顶帽沿上翘的粗皮质牛仔帽,并让他嘴上叼个烟斗,烟斗上有一缕烟雾。保持图片的其它元素不变。 Prompt: Put him in a rugged denim jacket, open to show the T-shirt and design he was originally wearing, add a thick leather cowboy hat with an upturned brim, and have him holding a smoking pipe with a wisp of smoke. Keep the other elements of the picture unchanged. 5. **仅提示词 + LoRA 换头、换装等。Prompt + LoRA to do Tryon / Tryoff and Faceswap.** 提示词:用图2的女士的脸,完全替换掉图1女士的脸。加 bfs_head_v1 LoRA 权重 0.75 (0.6-0.9)。 Prompt: Use the face of the woman in picture 2 to completely replace the face of the woman in picture 1. (model + lora - bfs_head_v1 weight = 0.75) 6. **通过 Mask + LoRA 实现图像的区域精准编辑。Precise regional image editing using Mask + LoRA.** (提示词和头像图片同上。The prompt and Face picture 2 are the same as above.) 与 V1 / V2 版本模型相同,The same with V1 / V2 vesrion. 或者参考 B 站如下大佬们的视频, Please refer to UP's video as below : 感谢:[@**T8star-Aix**](https://space.bilibili.com/385085361), [@**AI-KSK**](https://space.bilibili.com/110353151), [@**黑鹤001**](https://space.bilibili.com/515231056), [@**蓝色多脑盒**](https://space.bilibili.com/1450124458), [@**初级AAA**](https://space.bilibili.com/478987143), [@**山竹老师AIGC**](https://space.bilibili.com/158424637), [@**炮老师的小课堂**](https://space.bilibili.com/397686377), [@**HyLan_L**](https://space.bilibili.com/591877893), [@**雪煮松风**](https://space.bilibili.com/692784900), [@**冰缘排骨**](https://space.bilibili.com/3546582953757144), [@**暴躁小白兔学AI**](https://space.bilibili.com/3690991840135491) 以及 [@**活力网TV**](https://space.bilibili.com/92055552), 全平台统一号的 [@**CommintAI**](https://space.bilibili.com/158429672) 等一众社区大佬对本模型的各种技术评测、详细使用介绍及进一步微调提升等方面的建议和支持。 Also on: [Modelscope](https://modelscope.cn/models/wikeeyang/Flux2-Klein-9B-True-V3) 感谢:[@**亮亮rayne**](https://www.linkedin.com/in/2941b192),[@**GuangyuanSD**](https://huggingface.co/GuangyuanSD) 在模型调制优化过程一如既往的给与技术、构图、美学、社群等方面的指导和支持。 Thanks to [@**亮亮rayne**](https://www.linkedin.com/in/2941b192) and [@**GuangyuanSD**](https://huggingface.co/GuangyuanSD) for their usual guidance and support in the model tuning and optimization process, covering technology, composition, aesthetics, community, and more. 本模型请在遵循 black-forest-labs 公司非商业许可 ([FLUX Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.2-klein-9B/blob/main/LICENSE.md)) 下使用。 This model falls under the [FLUX Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.2-klein-9B/blob/main/LICENSE.md). **如果您喜欢我的模型,请支持 ❤️ 我以获得更多的算力来调优模型。** **If you like my models, please support ❤️ me for more computing resources to do finetuning work.** [![wikeeyang](ko-fi-wikeeyang.jpg)](https://ko-fi.com/wikeeyang)![Wechat](Wechat-Sponsor-Code.jpg)

Modality
text->image
License
apache-2.0
Open source
Yes

Open Flux2-Klein-9B-True-V3 in AIniverse

Compare versions, read real ratings, save to your stack.

Open in App