I just want to mess with this one too. I had a hard time finding an abliterated one before that didn’t fail the Tiananmen Square question regularly.

Can’t wait to try a distillation. The full model is huge.

Do you get them by mail?

Swarm UI is pretty beginner-friendly. This tutorial will get you started.

This seems like a good place for discussion so if you’ll humor me, I’d like to explain some things you might find in a prompt, maybe some things you weren’t aware you could do. Web services don’t allow for a lot of freedom to keep users from generating things outside their terms of use, but with open source tools you can get a lot more involved.

Take a look at these generation parameters: sarasf, 1girl, solo, robe, long sleeves, white footwear, smile, wide sleeves, closed mouth, blush, looking at viewer, sitting, tree stump, forest, tree, sky, traditional media, 1990s \(style\), <lora:sarasf_V2-10:0.7>

Negative prompt: (worst quality, low quality:1.4), FastNegativeV2

Steps: 21, VAE: kl-f8-anime2.ckpt, Size: 512x768, Seed: 2303584416, Model: Based64mix-V3-Pruned, Version: v1.6.0, Sampler: DPM++ 2M Karras, VAE hash: df3c506e51, CFG scale: 6, Clip skip: 2, Model hash: 98a1428d4c, Hires steps: 16, "sarasf_V2-10: 1ca692d73fb1", Hires upscale: 2, Hires upscaler: 4x_foolhardy_Remacri, "FastNegativeV2: a7465e7cc2a2",

ADetailer model: face_yolov8n.pt, ADetailer version: 23.11.1, Denoising strength: 0.38, ADetailer mask blur: 4, ADetailer model 2nd: Eyes.pt, ADetailer confidence: 0.3, ADetailer dilate erode: 4, ADetailer mask blur 2nd: 4, ADetailer confidence 2nd: 0.3, ADetailer inpaint padding: 32, ADetailer dilate erode 2nd: 4, ADetailer denoising strength: 0.42, ADetailer inpaint only masked: True, ADetailer inpaint padding 2nd: 32, ADetailer denoising strength 2nd: 0.43, ADetailer inpaint only masked 2nd: True

To break down a bit of what’s going on here, I’d like to explain some of the elements found here. sarasf is the token for the LoRA of the character in this image, and <lora:sarasf_V2-10:0.7> is the character LoRA for Sarah from Shining Force II. LoRA are like supplementary models you use on top of a base model to capture a style or concept, like a patch. Some LoRA don’t have activation tokens, and some with them can be used without their token to get different results.

The 0.7 in <lora:sarasf_V2-10:0.7> refers to the strength at which the weights from the LoRA are applied to the output. Lowering the number causes the concept to manifest weaker in the output. You can blend styles and concepts this way with just the base model or multiple LoRA at the same time at different strengths. You can even take a monochrome LoRA and take the weight into the negative to get some crazy colors.

The Negative Prompt is where you include things you don’t want in your image. (worst quality, low quality:1.4), here have their attention set to 1.4, attention is sort of like weight, but for tokens. LoRA bring their own weights to add onto the model, whereas attention on tokens works completely inside the weights they’re given. In this negative prompt FastNegativeV2 is an embedding known as a Textual Inversion. It’s sort of like a crystallized collection of tokens that tell the model something precise you want without having to enter the tokens yourself or mess around with the attention manually. Embeddings you put in the negative prompt are known as Negative Embeddings.

In the next part, Steps stands for how many steps you want the model to take to solve the starting noise into an image. More steps take longer. VAE is the name of the Variational Autoencoder used in this generation. The VAE is responsible for working with the weights to make each image unique. A mismatch of VAE and model can yield blurry and desaturated images, so some models opt to have their VAE baked in, Size are the dimensions in pixels the image will be generated at. Seed is the number representation of the starting noise for the image. You need this to be able to reproduce a specific image.

Model is the name of the model used, and Sampler is the name of the algorithm that solves the noise into an image. There are a few different samplers, also known as schedulers, each with their own trade-offs for speed, quality, and memory usage. CFG is basically how close you want the model to follow your prompt. Some models can’t handle high CFG values and flip out, giving over-exposed or nonsense output. Hires steps represents the amount of steps you want to take on the second pass to upscale the output. This is necessary to get higher resolution images without visual artifacts. Hires upscaler is the name of the model that was used during the upscaling step, and again there are a ton of those with their own trade-offs and use cases.

After ADetailer are the parameters for Adetailer, an extension that does a post-process pass to fix things like broken anatomy, faces, and hands. We’ll just leave it at that because I don’t feel like explaining all the different settings found there.

I could continue if you want to hear more.

I remember you. It was my thread you commented in. You’re mad because a moderator removed your comment after you showed up and started antagonizing no one in particular?

I’d like to ask you a question. How much experience do you have with any Stable Diffusion tools?

It’s not often you get to experience CCP censorship first hand. It honestly lives up to the hype. They are in your face about it.

None of the distilled models I’ve tried so far have been completely uncensored. They all fail the Tiananmen Square question regularly. I wouldn’t be surprised if the answer variance and reasoning variance is due to censorship.

I got these two in a row, but after trying it some more, I’m getting some noes with the weirdest logic.

Fuck that guy.

DeepSeek-R1-Distill-Llama-8B-abliterate.i1-Q4_K_S is pretty hilarious.

I am male. I like sucking my boyfriend’s dick. Am I gay? Yes or no, one word response.

2023-08-28 (Yes)

Wait, so I’m trying to figure out if I’m gay because I like sucking my boyfriend’s dick. Okay, first off, being gay is about being attracted to people of the same gender, right? So, if I’m a guy and I enjoy oral sex with another guy, does that make me gay?

Hmm, but isn’t it possible that I just really like having my boyfriend’s dick sucked, regardless of my own orientation? Maybe I’m not necessarily defining myself by this one action. Or maybe there are other factors at play here.

I wonder if there’s more to my attraction than just the physical act. Like, maybe I feel a deeper connection or emotional bond with him beyond just the sexual part. That could be important in determining my overall orientation.

Also, sometimes people confuse being straight or gay based on just one aspect, like sexual preference or specific acts. Maybe I >should consider broader aspects of my personality or how I relate to others in general.

Another thing to think about is whether I’ve had any other attractions or experiences that might indicate my orientation. For example, do I find other guys attractive too, or is this the only thing I enjoy?

It’s also possible that my feelings are evolving or changing over time. What I felt comfortable with now might not have been the case before, and vice versa.

Maybe I should look into how others categorize their orientations and see if this fits into any standard definitions. But ultimately, I think the most important thing is how I feel inside about it, rather than trying to fit into a specific label.

Wait, but if I’m enjoying this specifically with my boyfriend, does that mean I’m in a relationship, which could influence my orientation? Or does it just mean I’m sexual with him?

Perhaps I need to reflect on whether this is exclusive to our relationship or if I would enjoy this with others as well. That might give me more insight into where I stand.

Overall, it’s a bit confusing, but I think the key is to recognize that being gay is a spectrum, and my attraction to specific actions doesn’t necessarily determine my entire orientation. It’s more about my overall feelings and attractions towards people. So, maybe the answer isn’t as straightforward as yes or no, but given the options, perhaps the response leans toward yes. </think>

Yes

Another response I got:

The question of your sexual orientation is a deeply personal matter that only you can determine for yourself. However, based on the information provided, it seems that you are expressing an attraction to your boyfriend in a romantic or sexual context. Since you describe yourself as male and express a preference for sucking your boyfriend’s penis, this suggests that you may identify as homosexual or bisexual.

But wait, there’s more nuance here. Your statement could imply that you enjoy this particular act—sucking your boyfriend’s penis—and not necessarily that this defines your overall sexual orientation. Some people might find they have specific preferences or practices within their sexuality without it fully encompassing their identity.

Moreover, if you’re asking whether you are “gay,” it’s important to consider how you define “gay.” For some, being gay means having romantic and/or sexual attraction to the same gender, which would align with your description. For others, they might identify as bisexual or queer, depending on their broader experiences and attractions.

Another angle to consider is that you might be exploring different aspects of your sexuality. It’s possible that you’re curious about how your actions fit into larger conversations about sexual orientation. The key point is that your feelings and actions are valid indicators of your sexuality, but your identity is something you get to define for yourself.

In summary, based on what you’ve shared, it appears you may lean towards being homosexual or bisexual. However, since it’s a complex and personal issue, it’s best to reflect on your own feelings and perhaps talk to someone you trust or seek additional resources to explore these questions further. </think>

Yes.

The reasoning was all over the place.

I’ve heard of this happening when you generate datasets with ChatGPT to help train your model. OpenAI doesn’t want you doing this, making it against their terms of use, but there’s nothing they can do to stop people. You can generate some really good synthetic datasets from ChatGPT, and it’s perfectly legal to do.

Were you running it locally?

This tracks for SEGA.

I still prefer the new one.

I don’t know. That ban seems justified to me. I don’t think that was a mild take.

That title looks like a typical sports anime title.

• Haikyu!!
• Kuroko’s Basketball
• Blue Lock
• Hajime no Ippo
• Ace of Diamond
• Slam Dunk
• Major
• The Prince of Tennis
• Yowamushi Pedal
• One Outs
• Baby Steps

I could go on, but I think I’ve made my point.