Klein does not have LoRAs like the PixelSmile for QIE2511, so I decided to train a set myself! like the QIE2511 version, this collection allows for fine‑grained and linear control over facial expressions while maintaining high character consistency.
❤️ Please give me some support
Whether this collection can be continuously updated will depend on everyone's feedback. If you like it, please like, follow and share to let me know your appreciation; If you want to support independent development, please consider buying me a cup of coffee to keep this motivation going!
🕹️About LORA :
Fully linearly controllable, fine‑tune images based on weights ( example: scared )，Some LoRAs may affect facial aging appearance; please add Age for auxiliary adjustment.
🎰Collection list :
The latest LORA ( supporters version )
---------------------- Historical LoRA ----------------------
happy
sad
surpriseed
disgusted
angry
vigilant
sad and resentful
Updating continuously ……
👾Support me please:
I've invested a great deal of time and money in repeatedly training, testing, and optimizing these models, aiming to make them worthy of every ❤.
All publicly released models are experimental versions, intended solely for learning and communication purposes. If you discover any obvious advantages or disadvantages, please post the images and leave a comment to inform me.
✨Supporters also get exclusive access to:
🔓Get early access to various latest experimental models
🔓 The unreleased full version of the model and dedicated workflows
🔓 Detailed usage tips and guides, as well as professional consulting support
🫡 May the AI-power be with you🫡 see you soon !
Description
Disclaimer: This model or workflow is experimental and intended for learning and communication purposes only. Do not use it for any commercial activities.Users bear full responsibility for the generated content, including its legality, ethical implications, or potential misuse.By using this model or workflow, you are deemed to have agreed to these principles. Please use it responsibly within the scope permitted by local laws.
FAQ
Comments (5)
⛲Wishing Pool: If you have any desired slider-LORA in mind, leave a message here to let me know. 👈
I will determine the next training target based on the number of requests, provided that the existing training list is completed first. 🥰
cameltoe slider team !
How about hand gestures, like Thumbs up/down, or 'V'' sign, middle-finger, Ok hand gesture? BTW, GREAT stuff so far!
TANLINES slider PLS, and skin hyper details, good job by the way
it's ridiculous your slider loras are text-to-image only, these loras would be useful for text-to-image models with no i2i ability like flux 1&2 D, pony, sdxl...etc.
but to train loras like these for models that have i2i ability, and in particular for klein which is one of the most used image editing models along Qwen Image, and make these loras only work for t2i is ridiculous. also uploading the worse versions while selling the better versions of the same loras is funny, you should upload limited models with full capabilities to convince people to buy your other ones, giving away a lora with fucked up results won't make me think I should pay.
I'm happy to pay for creators but I'm not comfortable with your practices at all, sorry.