❤️ Please give me some motivation
This is a collection of Slider-LORA, dedicated to creating unique visual concepts.; for more types of control functions, please check my other collections.
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 don't like it, I will discontinue it. If you want to support independent development, please consider buying me a cup of coffee to keep this motivation going!
🤖About LORA :
The weight is usually between ±6, the effects of positive weights and negative weights are in the example
click here to get Simple Guide. Help you master the skills of using slider-LORA faster
quality ( Supporter version )
lighting ( Supporter version )
colortone ( Supporter version )
height ( only for supporters )
colorful ( Supporter version )
weight ( only for supporters )
people ( Supporter version )
clothes size ( supporter version )
tattoos ( supporter version )
shoot ( Supporter version )
angle shot ( supporter version )
fisheye ( supporter version )
details ( supporter version )
👾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: My model or workflow is solely for learning and communication purposes and shall not be used for any commercial activities. All responsibilities for the generated content, including its legality, ethical implications, or potential misuse, are borne entirely by the user. By using this model or workflow, you agree to this principle. Please use it responsibly within the scope of local laws.
FAQ
Comments (13)
It doesn't work. I get several errors like these with your quality.safetensors and light.safetensors LoRAs with Klein 9b:
ERROR lora diffusion_model.single_blocks.19.linear2.weight shape '[4096, 16384]' is invalid for input of size 37748736I checked the sha256, so the files are not corrupted.
I tested both with flux-2-klein-9b.safetensors and flux-2-klein-9b-fp8.safetensors.
I added a comment on Patreon but am not sure if those comments are reviewed. So I'll ask here too. I purchased rather than became a monthly member (I detest subscriptions) and found the links to the safetensors files but no workflow even though the Patreon page states that an Exclusive workflow is included. Maybe I missed the link but I couldn't find it.
[Later]. I used the loras in a workflow but I made the mistake of thinking they would work with Image to Image. They don't, of course. With Text to Image they work perfectly and produce really good results. I don't know whether I am getting such good results because I'm using the paid versions but I'm happy with my purchase.
Thank you for your [Later]. As you said, the Patreon version has been retrained based on the current version, so it performs better in many aspects such as detail representation and generalization. Here is a list: https://www.patreon.com/collection/2023965 which can help you better understand the content of this collection, including the exclusive workflow, and I hope it will be helpful to you. Thank you again for your recognition, and wish you a good time.
@NO8D Thanks for your response. With regard to the workflow, it seems that it is not included with the purchase if you are not a subscribed member. I still think that's not made very clear as I was fully expecting it to be included in my downloads. With that said, I did slot the Lora into a text to image workflow and, with a bit of juggling with models and settings, got some really impressive results.
@Dumcluck51 I have already marked "supporters only" in the description. This should help more people clarify the relationships. Thank you for your feedback. Additionally, if there are any other LORAs you need for your work, please feel free to let me know.
@NO8D Thanks again for responding. Not to labour the point excessively but anyone who buys your product might consider them self a "supporter" when what you mean is a subscriber. Anyhow, with regard to your request for Lora suggestions: my greatest need is for a reliable First/Last frame image generator. I know there are various workflows out there to do this but I have not found one that works for me. I want to load an image (SDXL/F2K9B/Qwen/ZIT - whatever) and describe the person in that image in a different pose while maintaining the background, clothing, hairstyle. etc. of the original image.
@Dumcluck51 In my heart, both purchasers and subscribers are supporters, because you are all supporting my work with practical actions, and I can invest the donations into research on new models or workflows. However, I am currently focusing on the field of image generation and have no plans to start working on videos for the time being. But recently, LTX2.3 has made me a bit tempted, and I will pay close attention to it.
@NO8D Sorry I might not have made my point(s) very well. I was saying precisely what you are saying - that both purchasers (without your Patreon subscription) and subscriber (with a Patreon subscriber account) are supporters. But purchasers are not getting the workflow that you give to subscribers. I hope that's made the point better. Again, back to my Lora suggestion: I am looking for an image generator, not a video. The video comes later when I use the First and Last frame images in a WAN 2.2 workflow which is not using the Lora I described. Again, I hope that's clarified now.
@Dumcluck51 you're being very clear. this has to be an automated robot talking, because i can't understand why they're not understanding your very simple problem otherwise.
@cufdjrookibivvzgkt384 You're right. I have some social difficulties, and both reading and writing are a bit challenging for me. I'm overcoming my problems by practicing writing prompts, which is also one of the reasons I'm researching AI.
@Dumcluck51 I'm sorry, I misunderstood what you meant earlier. Now I get it. Thank you for your patience. I think this is a very interesting requirement. I will try to look into it and post the results on Patreon to see everyone's feedback.
@NO8D Thanks - I will be interested to see what comes of my suggestion for a FLF Image Generator. I do think it would be popular and, if effective, people might pay for it as I did for your toolkit.