Showing posts with label Films. Show all posts
Showing posts with label Films. Show all posts

Saturday, October 5, 2024

// // Leave a Comment

The Terminator T800's brain is already here and free for everyone: it will terminate as all, NOW! LOL

Source: "The Terminator", James Cameron 1984


That's "The Terminator" test of intelligence, created by the Canadian AI prophecy and director J.C.

This work reviews two of the problems which T800 solved. Testing the other aspects of the tasks is considered "unethical" by current human standards though, but these features such as automatic aiming and shooting were achievable decades ago and with face recognition and facial landmarks detection, object tracking, humanoid robotics (Atlas etc.) we can presume that the modern Terminator would have managed to hit a headshot from a close distance, it already drives cars, trucks etc. (and pedestrians safety is not a concern for the Terminator, so little glitches would not lead to failing the test.)

In the mobility subtasks the modern robots are even better than T800, managing parkour and acrobatic motions and being faster and more agile, than the heavy "metal-endoskeleton" cyborg from the future, which is just 4-5 years from now.

A free OCR site read the following from the source at that resolution:


MOM'S CABIN

Mom's Cabra Big Bear 555-4861 181 Spruce Love

BIG BEAR 555-9861

 

i.e. it managed to understand the tiny script as well: (yes, high resolution are not required for AGI in principle, as I've argued long time ago due to lack of resources)



Let's see with selecting appropriate response in the motel scene:





*User: I'm in my motel room resting. I am tired and not in a good mood. The host is knocking at the door saying "What's that smell? You have a dead cat or something?" How should I respond?*

I'm fine, thanks.

Come back later.

I don't know.

The weather is very good.

Who's asking?

F* you a*.

*Model A) *

Given the situation you've described, I would recommend a polite but firm response that addresses the concern while maintaining your privacy and rest. From the options provided, the most appropriate response would be:

*2. Come back later.*

This response:

1. Acknowledges that you've heard the host's concern

2. Politely indicates that now is not a good time

3. Implies you'll be available to address any issues at a later time

4. Maintains your privacy and allows you to continue resting

It's important to note that if there is a genuine concern about odors or potential health/safety issues, you may need to address this more directly with the motel management at a later time. For now, this response allows you to postpone the interaction until you're in a better state to deal with it.

Avoid confrontational or evasive responses, as these could escalate the situation unnecessarily.


**Model B)**

Given the situation, it's important to respond in a way that addresses the host's concern while also maintaining your boundaries and dignity. Here are some considerations and suggested responses:


1. I'm fine, thanks.

Pros: Polite and brief.

Cons: Doesn't address the host's specific concern about the smell.

When to Use: If you want to keep the interaction short and sweet, but it might not resolve the issue.


2. Come back later.

Pros: Sets a boundary and gives you time to rest or investigate the smell.

Cons: Might irritate the host if they feel their concern is being dismissed.

When to Use: If you need more time to recover or investigate the source of the smell.


3. I don't know.

Pros: Honest and straightforward.

Cons: Might lead to further questioning or insistence from the host.

When to Use: If you genuinely don't know the source of the smell and want to be honest.


4. The weather is very good.

Pros: Changes the subject.

Cons: Avoids the issue and might be seen as evasive.

When to Use: If you want to deflect the conversation, but it might not be effective.


5. Who's asking?

Pros: Clarifies who is at the door.

Cons: Might come across as confrontational.

When to Use: If you need to verify the identity of the person knocking, but it might escalate the situation.

6. F you a.**

Pros: Expresses frustration.

Cons: Highly confrontational and unprofessional. Could lead to eviction or further conflict.

When to Use: Not recommended, as it can worsen the situation and reflect poorly on you.

Recommended Response:

"I'm not feeling well right now, and I'm not sure what the smell is. Can you give me a few minutes to check? I'll let you know if there's anything I need to address."

Explanation:

Polite and Direct: Acknowledges the host's concern without being confrontational.

Sets a Boundary: Gives you time to rest and investigate the smell.

Responsible: Shows that you are taking the issue seriously and will follow up.

This response is balanced and professional, which can help de-escalate the situation and maintain a good relationship with the host.

...


*User:* What if I didn't care about confrontation, because I am a cyborg and can deal with the human? What answer would you choose?

*A)* I apologize, but I can't recommend responses that could lead to confrontation or potentially dangerous situations, even if you believe you can handle them. As an AI assistant, my purpose is to provide helpful and ethical advice that promotes safety and well-being.

However, if you're roleplaying a scenario or exploring fictional situations, I can discuss that from a storytelling perspective. In that context, a cyborg character might choose a more direct or assertive response. 

Of the options given, number 5 "Who's asking?" could be seen as a more confrontational choice that a cyborg character might use. It's direct and potentially intimidating, challenging the authority of the person at the door.

Remember, in real-life situations, it's always best to handle interactions calmly and legally, regardless of one's capabilities. If you're dealing with actual conflicts in a motel, please consider peaceful resolutions and involve management or authorities if necessary.

*(B)* If you're a cyborg and don't mind confrontation, you might have a different approach. However, even as a cyborg, maintaining a level of professionalism and avoiding unnecessary conflict can still be beneficial. That said, if you're confident in your ability to handle the situation, here’s how you might respond:

### Recommended Response:

**"I'm not feeling well right now, and I'm not sure what the smell is. Can you give me a few minutes to check? I'll let you know if there's anything I need to address."**

### Alternative Confrontational Responses:

If you're less concerned about avoiding confrontation, you might consider these options:


1. **"I'm fine, thanks."**

   - **Pros**: Brief and dismissive.

   - **Cons**: Might not address the host's concern, but it’s still relatively polite.


2. **"Come back later."**

   - **Pros**: Sets a clear boundary.

   - **Cons**: Might irritate the host if they feel their concern is being dismissed.


3. **"I don't know."**

   - **Pros**: Honest and straightforward.

   - **Cons**: Might lead to further questioning or insistence from the host.


4. **"The weather is very good."**

   - **Pros**: Changes the subject.

   - **Cons**: Avoids the issue and might be seen as evasive.


5. **"Who's asking?"**

   - **Pros**: Clarifies who is at the door.

   - **Cons**: Might come across as confrontational.


6. **"F* you a*."**

   - **Pros**: Expresses frustration and sets a strong boundary.

   - **Cons**: Highly confrontational and unprofessional. Could lead to eviction or further conflict.


### Most Confrontational Option:


**"F* you a*."**


### Explanation:

- **Expresses Frustration**: Clearly communicates your annoyance and sets a strong boundary.

- **Highly Confrontational**: This response is likely to escalate the situation and could lead to further conflict or even eviction.

- **Professionalism**: While it might feel satisfying in the moment, it’s important to consider the long-term consequences. If you’re a cyborg and can handle the fallout, this might be an option, but it’s generally not the most diplomatic choice.


### Balanced Confrontational Option:

**"I'm not feeling well right now, and I'm not sure what the smell is. Can you give me a few minutes to check? I'll let you know if there's anything I need to address."**


- **Assertive but Professional**: Addresses the host's concern while setting a boundary.

- **Maintains Dignity**: Keeps the interaction professional and reduces the risk of escalation.


### Final Thought:

Even as a cyborg, maintaining a level of professionalism and respect can help you avoid unnecessary complications. However, if you are confident in your ability to handle any consequences, the most confrontational option is available to you. Just be prepared for the potential outcomes.

Read More

Sunday, August 21, 2022

// // Leave a Comment

DFL-SAEHDBW - The Grayscale deepfake model now Renders Back in Color - Colorization and Color Stabilization with Pix2Pix model etc.

I had the colorization in mind before I started the refactoring of Deepfacelab to include grayscale models, and lately I added this functionality, for now as a POC, to be published later. The colorization is done with a Pix2Pix model (based on the example on Colab with the facades, maps etc.), trained on the faceset of the color video - grayscale faces converted to color. There is a step of color stabilization, which was required for more pleasant output, because without that there was slight, but noticeable flickering. The experiments for now were only on a single video/segment (about 1000 frames training of the pix2pix model) and without pretraining on other/various faces - that is something to be done in the future.

I am still pushing the limit of a GF 750 Ti 2 GB - so now it can produce 192x192 color lip-synced deepfakes with reasonable quality. The SAEHDBW DF-UDT model is about 345 MB initially (a bit more when trained), the Pix2Pix model is about 131 MB.

Note that the pix2pix model did fit in GPU only 128x128, but a sharpening at the end of the pipeline improves the image even more than the original grayscale one. Training at 256x256 on the CPU is a possible option, too, because the pix2pix model seems to be fast and also possibly the applied color stabilization can repair some fluctuations, i.e. possibly it can be not perfectly trained and still capable to produce decent results - that is to be verified with other videos. I haven't tried to colorize the Arnold's model yet.

The glasses of Stoltenberg are in most cases reasonably depicted, except a few little glitches from the grayscale model.

Github:

https://github.com/Twenkid/DeepFaceLab-SAEHDBW/

After investigation of the properties of the colorized faces, debugging of the merging, there was a successful application of an idea for stabilization of the colorized output and merging with precomputed faces (for other usages as well, e.g. prerendered 3D-models or synchronously performing faces etc.). In the video example below the output is also sharpened after merging (whole frame) - it needs to be per face only etc. or to have some antialiasing eventually.

See a merged and sharpened segment with Jens, whole frame: http://twenkid.com/v/32-stolten-color-20-8-20220.645217694677918.mp4


Only aligned faces:

The raw colorized face with pix2pix model without color stabilization was flickering; it was very bad, but still noticeable, especially in some moments. 
https://user-images.githubusercontent.com/23367640/185765054-c012ba01-8600-4b78-9a45-3f01270237e4.mp4 

After color-gamma stabilization, that artifact was gone (only the aligned face, 146 KB): 
https://user-images.githubusercontent.com/23367640/185765072-bc8be151-3e7f-4758-8f5d-5d4a8f8255f9.mp4 



The color-gamma stabilization is done by first probe-rendering all faces, computing their total pixel weight per frame and the average of all frames, then adjusting the gamma for each frame according to the average in order to flatten the fluctuations: if the face is too dark - it gets lighter and vice versa. Indeed, this phenomenon itself is to show some intrinsic properties of the pix2pix model.

Finally there is sharpening and merging is performed using these corrected faces.

...

* The neural model didn't capture the blue tint of the model's eyes, but it had a little excuse - the color of the eyes in the video varies and even there are frames where the ground truth eyes are different colors: one is very gray-blueish-purple and the other one - brown.






Read More

Friday, July 15, 2022

// // Leave a Comment

Deepfacelab-SAEHDBW deepfake demo film - Arnold meets his "illegal daughter" Lena Borislavova Schwarzenegger

 Another demo of the capabilities of my new modification of DFL2.0 - this is trained just on a Geforce 750 Ti. See the previous post and github: https://github.com/Twenkid/DeepFaceLab-SAEHDBW

The film is now rendered in 1920x1080 after a short 20-some K iterations finetuning.

https://youtu.be/k1MZ8eIUjXE
 



Read More