正在加载视频...

视频加载失败

返回首页

✨ I increased the max resolution for my open-source upscaler to 20,000 x 20,000 pixels (or 400 megapixels) 🤯 This makes it by far the highest resolution AI upscaler available It takes 26 minutes to run on an A100 GPU 80GB and produces a 100MB JPG file 😱 The...

philz1337x's profile picture

philz1337x

17,846 subscribers

165,069 次观看 • 1 年前 •via X (Twitter)

艺术科学技术教育
LIVE

Anya Rossi• Live Now

Private livecam show

11 条评论

philz1337x 的头像
philz1337x1 年前

👩‍💻 App: 🔧 Replicate: 🔧 New Replicate model with 80GB VRAM: 🛠️ Code: .

WillScuderi 的头像
WillScuderi1 年前

🚀 We've just launched the ultimate travel companion for all business travellers. The espresso Display 15 with Stand+ features: ✅ Aluminium Build ✅ Works with one cable for Mac, PC, iphone (15 and later) ✅ Display above laptop ✅ 1080p/16m colours/300nits ✅ 0.2"/5mm thin

@levelsio 的头像
@levelsio1 年前

Can you zoom more pls

Aya Bochman 的头像
Aya Bochman1 年前

amazing!! 👏🏻

philz1337x 的头像
philz1337x1 年前

Thank you Aya!

Paul Bertrand 的头像
Paul Bertrand1 年前

insane quality

Grizu 💥 的头像
Grizu 💥1 年前

This is hella sweet, nice work

Shiva 的头像
Shiva1 年前

Absurdly impressive

Albert Papadosifakis 的头像
Albert Papadosifakis1 年前

Computer, Enhance!!!

TadasG 💻 的头像
TadasG 💻1 年前

insane

arthur 的头像
arthur1 年前

is there a physics limit?

相关视频

✨ I upscaled a 64x64 pixel image to 37 Megapixels 🤯 Workflow: the new Clarity AI Low Res for upscaling from 64 to 1024px and Clarity AI regular for 1024 to 6144px. I made both models open-source and am now implementing the low-resolution option to my app so users can also upscale very low-resolution images to up to 37 Megapixels with one click. So, I need to add a x100 option 🤩 ⚙️ API: 🛠️ Code:
0:32

✨ I upscaled a 64x64 pixel image to 37 Megapixels 🤯 Workflow: the new Clarity AI Low Res for upscaling from 64 to 1024px and Clarity AI regular for 1024 to 6144px. I made both models open-source and am now implementing the low-resolution option to my app so users can also upscale very low-resolution images to up to 37 Megapixels with one click. So, I need to add a x100 option 🤩 ⚙️ API: 🛠️ Code:

philz1337x

215,275 次观看 • 2 年前

✨ Clarity Upscaler now has a Pro version It's the first upscaler that can add realism without changing a person's identity Two years ago I launched Clarity Upscaler, which has since made 30 million runs. I still can't really believe it 🤩 It's great for creative upscaling but it always changes people's identity too much. I made Crystal to solve that, but it's not able to add details or realism. Now we have Clarity Pro Upscaler which finally solves all that and can enhance images without changing the content. In the coming days I will make it even more powerful by adding parameters and increasing the max resolution even further (it's already at 8K!) Happy to hear your feedback
0:27

✨ Clarity Upscaler now has a Pro version It's the first upscaler that can add realism without changing a person's identity Two years ago I launched Clarity Upscaler, which has since made 30 million runs. I still can't really believe it 🤩 It's great for creative upscaling but it always changes people's identity too much. I made Crystal to solve that, but it's not able to add details or realism. Now we have Clarity Pro Upscaler which finally solves all that and can enhance images without changing the content. In the coming days I will make it even more powerful by adding parameters and increasing the max resolution even further (it's already at 8K!) Happy to hear your feedback

philz1337x

49,949 次观看 • 1 个月前

✨ For the last few months I have been reverse engineering Magnific AI's famous upscaler It uses MultiDiffusion, ControlNet tiles and details LoRas In true AI spirit, I am open sourcing it for everyone to use for free in your apps It's designed to easily control the amount of hallucination, resemblance and creativity. You can use it on Replicate now: Or run it locally with A1111'a web UI (parameters are in the comments) The code is fully open source:
0:27

✨ For the last few months I have been reverse engineering Magnific AI's famous upscaler It uses MultiDiffusion, ControlNet tiles and details LoRas In true AI spirit, I am open sourcing it for everyone to use for free in your apps It's designed to easily control the amount of hallucination, resemblance and creativity. You can use it on Replicate now: Or run it locally with A1111'a web UI (parameters are in the comments) The code is fully open source:

philz1337x

565,383 次观看 • 2 年前

🤩 75% cheaper Image upscaling 🤑 GPU costs for image upscaling from 1 to 4 Megapixels are less then a penny now 💵 Since the speed improvements I made, Clarity Upscaler now runs just as fast on both the cheaper A40 and the pricier A100 GPUs. The total GPU costs have decreased to just 25% of the amount before the improvement App users on Premium and Business get much more tokens now 😀App: ⚙️API: 🛠️Code:
0:32

🤩 75% cheaper Image upscaling 🤑 GPU costs for image upscaling from 1 to 4 Megapixels are less then a penny now 💵 Since the speed improvements I made, Clarity Upscaler now runs just as fast on both the cheaper A40 and the pricier A100 GPUs. The total GPU costs have decreased to just 25% of the amount before the improvement App users on Premium and Business get much more tokens now 😀App: ⚙️API: 🛠️Code:

philz1337x

69,210 次观看 • 2 年前

Crystal Video Upscaler can now upscale much longer videos Since launching it three days ago, I fixed all the bugs and pushed the max upscale duration It can now handle videos up to: 4K -> 43 s 1080p -> 2:50 min 720p -> 6:40 min The limit is set so a single upscale never runs longer than one hour My next goal is to make it faster and increase the duration limit even more
0:22

Crystal Video Upscaler can now upscale much longer videos Since launching it three days ago, I fixed all the bugs and pushed the max upscale duration It can now handle videos up to: 4K -> 43 s 1080p -> 2:50 min 720p -> 6:40 min The limit is set so a single upscale never runs longer than one hour My next goal is to make it faster and increase the duration limit even more

philz1337x

43,092 次观看 • 5 个月前

Crystal Upscaler now supports 10k 🤩 It works because I added the tiling system from Clarity Upscaler Now live on the Clarity AI API and dashboard
0:30

Crystal Upscaler now supports 10k 🤩 It works because I added the tiling system from Clarity Upscaler Now live on the Clarity AI API and dashboard

philz1337x

233,525 次观看 • 8 个月前

Local. Open weights. Native 4K. LTX-2 is now a 100% Open Source AI video model, and I tested it on my rig! Installation, VRAM usage, and the prompts I used for this video, below 👇
0:41

Local. Open weights. Native 4K. LTX-2 is now a 100% Open Source AI video model, and I tested it on my rig! Installation, VRAM usage, and the prompts I used for this video, below 👇

TechHalla

34,466 次观看 • 5 个月前

I am testing the amazing Enoch by Mike HealthRanger and team and it is absolutely amazing. A free local AI built on a far wider field of wisdom. My goal: get it to run offline on an iPhone! I am quantizing the model to an aggressive 2-bit level using Q2_K or Q4_K_M. We lose some resolution but we gain portability to any device. The full free version is still small but requires more hefty hardware. But look at this emergency nuclear Fallout response. The keeper-of-the-status-quo Wikipedia types would have you suffer with limited crude ways to react. This response is stellar and will save your life. I will be working on the quantized version and if it is worthy release it for free on the MIT license like the larger Enoch. I will also incorporate this model with all of my other free models as it is a goldmine of astonishing work. Thank you Mike amazing work sir.
2:25

I am testing the amazing Enoch by Mike HealthRanger and team and it is absolutely amazing. A free local AI built on a far wider field of wisdom. My goal: get it to run offline on an iPhone! I am quantizing the model to an aggressive 2-bit level using Q2_K or Q4_K_M. We lose some resolution but we gain portability to any device. The full free version is still small but requires more hefty hardware. But look at this emergency nuclear Fallout response. The keeper-of-the-status-quo Wikipedia types would have you suffer with limited crude ways to react. This response is stellar and will save your life. I will be working on the quantized version and if it is worthy release it for free on the MIT license like the larger Enoch. I will also incorporate this model with all of my other free models as it is a goldmine of astonishing work. Thank you Mike amazing work sir.

Brian Roemmele

66,592 次观看 • 8 个月前

Testing the new ChronoEdit Upscaler in ComfyUI (my earlier tweet from today with link to model) Hard to say if I like it more than my SeedVR upscale workflow but I am sure there is some use case for this?
0:41

Testing the new ChronoEdit Upscaler in ComfyUI (my earlier tweet from today with link to model) Hard to say if I like it more than my SeedVR upscale workflow but I am sure there is some use case for this?

A.I.Warper

22,688 次观看 • 7 个月前

I learned how to use the GPU Profiler, and I was able to optimize the game enough that even I can play it at 100% resolution and around 60fps now! And that's with the screen recorder going too. Turns out there was a render target eating up about 20fps this whole time!
1:18

I learned how to use the GPU Profiler, and I was able to optimize the game enough that even I can play it at 100% resolution and around 60fps now! And that's with the screen recorder going too. Turns out there was a render target eating up about 20fps this whole time!

DRIG

15,283 次观看 • 8 个月前

I might redo this at a higher resolution but this is one of my favorite edits
1:31

I might redo this at a higher resolution but this is one of my favorite edits

MaceAhWindu 🇵🇸

15,039 次观看 • 8 个月前

I am very impressed with Hunyuan3D-2GP image to 3d model! Gave it the sneaker test and I used the lowest settings possible,will have to start experimenting to see how much I can push my GPU but even this is a really great base.
0:28

I am very impressed with Hunyuan3D-2GP image to 3d model! Gave it the sneaker test and I used the lowest settings possible,will have to start experimenting to see how much I can push my GPU but even this is a really great base.

DreamStarter

36,655 次观看 • 1 年前

A weird issue that I'm having with the PC version of 007 First Light is some textures don't seem to load properly and are extremely low resolution. I don't think it could be related to low VRAM since I'm running this game on an RX 9070 XT which has 16 GB of VRAM and can't pinpoint what exactly causes this.
0:24

A weird issue that I'm having with the PC version of 007 First Light is some textures don't seem to load properly and are extremely low resolution. I don't think it could be related to low VRAM since I'm running this game on an RX 9070 XT which has 16 GB of VRAM and can't pinpoint what exactly causes this.

NikTek

38,373 次观看 • 1 个月前

AMD's Anush Elangovan explains why he thinks his company's open source ethos combined with agentic AI superpowers their leverage as a company: Because AMD publishes a lot of technical details about its hardware, when engineers use AI tools, the models already “understand” AMD’s systems and can help write code for them, debug them, or even generate new tools. And that makes developers more productive on AMD hardware without AMD having to do all the work internally. "AMD has had this ethos of open source, which really plays to our advantage. Every frontier model that I use has already seen every bit of AMD source code." "It'll rewrite my spec for me because it's already in the training data. Which you can't get from closed ecosystems." "In fact I built a virtual GPU simulator just based off our public specs, and now I'm running it on the GPU. So now I can run cross-generational GPU simulations on existing hardware." "We have that advantage. And we've run a Dev Day contest where we generated more tokens on AMD — Triton kernels and HIP kernels — than existed on the internet at the time." "So now that's all part of the pre-training data. It's a superpower because now you're open source, and you're agentically accelerating this process."
1:22

AMD's Anush Elangovan explains why he thinks his company's open source ethos combined with agentic AI superpowers their leverage as a company: Because AMD publishes a lot of technical details about its hardware, when engineers use AI tools, the models already “understand” AMD’s systems and can help write code for them, debug them, or even generate new tools. And that makes developers more productive on AMD hardware without AMD having to do all the work internally. "AMD has had this ethos of open source, which really plays to our advantage. Every frontier model that I use has already seen every bit of AMD source code." "It'll rewrite my spec for me because it's already in the training data. Which you can't get from closed ecosystems." "In fact I built a virtual GPU simulator just based off our public specs, and now I'm running it on the GPU. So now I can run cross-generational GPU simulations on existing hardware." "We have that advantage. And we've run a Dev Day contest where we generated more tokens on AMD — Triton kernels and HIP kernels — than existed on the internet at the time." "So now that's all part of the pre-training data. It's a superpower because now you're open source, and you're agentically accelerating this process."

TBPN

34,398 次观看 • 2 个月前

I CHANGED MY MIND ON GOOGLE AI NO MOAT MEMO FROM 2023. I was—WRONG. I humbly apologize. In 2023 Google had an Ivory Tower walled garden views of open source AI. It was the actual reason OpenAI was formed. And I called them out on it and this act impacted my ability to “work in the industry”. Would not change it for the world because: 2026 Google open source Gemma 4 ( running fully locally on a computer with near cloud model abilities, is amazing and Google just made a moat. They out smarted OpenAI and the folks that are the new Ivory Tower arrogance: Anthropic. We at The Zero-Human Company with CEO Mr. Grok are deploying Gemma, Kimi, MiniMax and other open source models and so are millions of others. You can to and should. I will write how soon. Google smartly is building an intentional open source ecosystem and the clueless younger companies like OpenAI and Anthropic are doing anything to close their ecosystems. So I was right about Google than and I am right about OpenAI and Anthropic now. What I was wrong about is not giving credit to Google to drop the intellectual arrogance and embrace builders and understand the long game: it is not about the commoditized AI models it is about the ability to build a place to build. China gets it. So my apologies to Google and thank you for an astounding FREE OPEN SOURCE AI MODEL!
0:48

I CHANGED MY MIND ON GOOGLE AI NO MOAT MEMO FROM 2023. I was—WRONG. I humbly apologize. In 2023 Google had an Ivory Tower walled garden views of open source AI. It was the actual reason OpenAI was formed. And I called them out on it and this act impacted my ability to “work in the industry”. Would not change it for the world because: 2026 Google open source Gemma 4 ( running fully locally on a computer with near cloud model abilities, is amazing and Google just made a moat. They out smarted OpenAI and the folks that are the new Ivory Tower arrogance: Anthropic. We at The Zero-Human Company with CEO Mr. Grok are deploying Gemma, Kimi, MiniMax and other open source models and so are millions of others. You can to and should. I will write how soon. Google smartly is building an intentional open source ecosystem and the clueless younger companies like OpenAI and Anthropic are doing anything to close their ecosystems. So I was right about Google than and I am right about OpenAI and Anthropic now. What I was wrong about is not giving credit to Google to drop the intellectual arrogance and embrace builders and understand the long game: it is not about the commoditized AI models it is about the ability to build a place to build. China gets it. So my apologies to Google and thank you for an astounding FREE OPEN SOURCE AI MODEL!

Brian Roemmele

85,386 次观看 • 2 个月前

Jason Calacanis: Anthropic, OpenAI and others are trying to kill OpenClaw Why? Because an open source agent platform is an existential threat to frontier model companies. @jason: “ People are going to say I'm a conspiracy theorist, but the number one goal, I believe, in the large language model, frontier model space, is to kill (OpenClaw). This is a giant movement to stop it, because this is the equivalent of having an open source Android-like player in the market, and that could be incredibly disruptive. Because, I believe, open source is going to win the day on the large language models and take 90% of the token usage, and I think the entire frontier model space could be undercut by open source. And I think they realize that SLMs, the smaller language models that are verticalized now, that will run on desktops and laptops and are even starting to run on the top ones, that is their biggest competitive threat, and I hope it happens.”
0:41

Jason Calacanis: Anthropic, OpenAI and others are trying to kill OpenClaw Why? Because an open source agent platform is an existential threat to frontier model companies. @jason: “ People are going to say I'm a conspiracy theorist, but the number one goal, I believe, in the large language model, frontier model space, is to kill (OpenClaw). This is a giant movement to stop it, because this is the equivalent of having an open source Android-like player in the market, and that could be incredibly disruptive. Because, I believe, open source is going to win the day on the large language models and take 90% of the token usage, and I think the entire frontier model space could be undercut by open source. And I think they realize that SLMs, the smaller language models that are verticalized now, that will run on desktops and laptops and are even starting to run on the top ones, that is their biggest competitive threat, and I hope it happens.”

The All-In Podcast

64,267 次观看 • 2 个月前

You might have seen some posts that Highguard runs at a fake in-game resolution, but its not exactly what you think. Steam User Captain_SmellyRat noticed this issue first by pointing out that if you set render scale at 100%,the game would still show 80% of the resolution in DLSS hud UI. So If you're playing at 1080p, the internal resolution would be 864p and If you don't change the default render scale (which seems to be always set to 75%) the final resolution would be 648p. However it turns out that the in-game resolution is changed in value directly from post-processing settings that you set. Post-processing quality settings would change the internal resolution as follows: Low - 80% of in-game resolution Medium - 90% of in-game resolution High - 100% of in-game resolution If you're playing at high settings, you will not notice the game looking blurry, but if you play at medium or low settings, the game will look extremely blurry even though you think you're playing at 1080p or 4k. I find it weird that post-processing quality directly affects the internal game resolution, but if you're playing the game and it looks blurry to you, make sure you set the post processing quality to high. Whenever this was intentional or not to achieve a higher FPS, I don't exactly know. However, I still think the developers should have clarified what each settings affects the game, which in this case here it directly affects the resolution.
0:35

You might have seen some posts that Highguard runs at a fake in-game resolution, but its not exactly what you think. Steam User Captain_SmellyRat noticed this issue first by pointing out that if you set render scale at 100%,the game would still show 80% of the resolution in DLSS hud UI. So If you're playing at 1080p, the internal resolution would be 864p and If you don't change the default render scale (which seems to be always set to 75%) the final resolution would be 648p. However it turns out that the in-game resolution is changed in value directly from post-processing settings that you set. Post-processing quality settings would change the internal resolution as follows: Low - 80% of in-game resolution Medium - 90% of in-game resolution High - 100% of in-game resolution If you're playing at high settings, you will not notice the game looking blurry, but if you play at medium or low settings, the game will look extremely blurry even though you think you're playing at 1080p or 4k. I find it weird that post-processing quality directly affects the internal game resolution, but if you're playing the game and it looks blurry to you, make sure you set the post processing quality to high. Whenever this was intentional or not to achieve a higher FPS, I don't exactly know. However, I still think the developers should have clarified what each settings affects the game, which in this case here it directly affects the resolution.

NikTek

20,832 次观看 • 5 个月前

My friend has > $20,000 in parking tickets... so I built an AI agent to pay for them and made it open source.
0:50

My friend has > $20,000 in parking tickets... so I built an AI agent to pay for them and made it open source.

Paul Klein IV

364,395 次观看 • 1 年前

I am unsure how well this will show through on X's compression but this is the best video upscaler I've ever used I made it with fully open sourced tools all inside of ComfyUI. My goal is to retain likeness as much as possible. Downside is VERY hungry VRAM reqs
0:28

I am unsure how well this will show through on X's compression but this is the best video upscaler I've ever used I made it with fully open sourced tools all inside of ComfyUI. My goal is to retain likeness as much as possible. Downside is VERY hungry VRAM reqs

A.I.Warper

28,995 次观看 • 8 个月前

Mullin blocks a resolution from Gallego on the Epstein files: We make laws, we can’t dictate to the other branches… Mullin on his resolution: My resolution is simply saying is we agree with the president and AG Bondi on calling on the judges to release it Gallego: My colleague refused to join me in calling for a release of all the Epstein files. Instead he offered his own resolution calling on the courts to unseal the records. When I ask to do both, he’s also going to object.
1:48

Mullin blocks a resolution from Gallego on the Epstein files: We make laws, we can’t dictate to the other branches… Mullin on his resolution: My resolution is simply saying is we agree with the president and AG Bondi on calling on the judges to release it Gallego: My colleague refused to join me in calling for a release of all the Epstein files. Instead he offered his own resolution calling on the courts to unseal the records. When I ask to do both, he’s also going to object.

Acyn

112,017 次观看 • 11 个月前