Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

extremely precise control just landed to Krea-2 as a LoRA! 🎨 krea2-turbo-bbox adds precise layout-controlled generation to Krea 2: drag the boxes, regenerate, the composition obeys, text boxes included cooked by jimmycarter 🧑‍🍳 ▶️ on Spaces

HuggingApps's profile picture

Hugging Apps

4,336 subscribers

27,941 Aufrufe • vor 1 Monat •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

9 Kommentare

Profilbild von TheOneHong阿康
TheOneHong阿康vor 1 Monat

so now ideogram 4 is officially declared to be depreciated, this does exactly what they achieved

Profilbild von DeDi
DeDivor 1 Monat

布局控制LoRA提升图像生成精确度

Profilbild von Kutflow
Kutflowvor 1 Monat

Can this be used to remove things from an image?

Profilbild von Shahar Nechmad
Shahar Nechmadvor 1 Monat

Super cool. Dragging boxes feels much more natural than fighting a prompt to get the layout right. Is there a way to also change the depth layout - meaning, what will be behind or in front of the other boxes?

Profilbild von Adel Bucetta
Adel Bucettavor 1 Monat

precise control is one thing, but can you scale this kind of output to real-world complexity? that's the test for most ai innovations

Profilbild von Jackburton-Dz
Jackburton-Dzvor 1 Monat

I taught the president was dead? 🤭

Profilbild von Kubilây Ân Artwork
Kubilây Ân Artworkvor 1 Monat

26 gb lora ?!?!?!?

Profilbild von darkblack
darkblackvor 1 Monat

Perfect perfect

Profilbild von AI Mastery Guide
AI Mastery Guidevor 1 Monat

Dragging boxes to control the layout is way easier than prompting for it.

Ähnliche Videos

Krea 2 Open-Source is now available on fal The most aesthetic open-source image model, released with open weights Turbo delivers fast, polished text-to-image at low step counts RAW serves as the malleable base checkpoint for LoRA training
0:59

Krea 2 Open-Source is now available on fal The most aesthetic open-source image model, released with open weights Turbo delivers fast, polished text-to-image at low step counts RAW serves as the malleable base checkpoint for LoRA training

fal

47,744 Aufrufe • vor 3 Monaten

🎨 I trained 999 Style LoRAs with the fal Krea 2 Trainer. Every single image in this video is a different LoRA. That's 999 unique Style LoRAs, each trained for just 100 steps at 0.00035 LR, taking an average of ~30 seconds to train. As I said before, Krea 2 continues to prove that it's an incredible model for open-source Style LoRAs. Next week I'll be sharing even more LoRAs, along with a few surprises.
1:30

🎨 I trained 999 Style LoRAs with the fal Krea 2 Trainer. Every single image in this video is a different LoRA. That's 999 unique Style LoRAs, each trained for just 100 steps at 0.00035 LR, taking an average of ~30 seconds to train. As I said before, Krea 2 continues to prove that it's an incredible model for open-source Style LoRAs. Next week I'll be sharing even more LoRAs, along with a few surprises.

ilker

12,794 Aufrufe • vor 3 Monaten

Ideogram announced Ideogram 4.0, a new SOTA open image generation model! > Ideogram 4.0 lands in the 8th spot on LM Arena and the 5th spot on Design Arena in the text-to-image category, and is getting close to Nano Banana Pro's performance. > Ideogram 4.0 features dense, accurate text rendering, native 2K resolution, active background transparency, and precise layout control.
0:55

Ideogram announced Ideogram 4.0, a new SOTA open image generation model! > Ideogram 4.0 lands in the 8th spot on LM Arena and the 5th spot on Design Arena in the text-to-image category, and is getting close to Nano Banana Pro's performance. > Ideogram 4.0 features dense, accurate text rendering, native 2K resolution, active background transparency, and precise layout control.

🚨 AI News | TestingCatalog

19,674 Aufrufe • vor 3 Monaten

The best way to bring the composition from your head into an image → Ideogram V4 + drawing bounding boxes in Comfy. The control here is quite unique. The model uses structured JSON so drawing bounding boxes to get the exact placement works very well. The model only needs 12 steps (turbo), so iterating with different seeds + very impressive text rendering capability leads me to say this is a state of the art open source image model right now. Using the 'Ideogram 4 Prompt Builder' node by Kijai.
0:49

The best way to bring the composition from your head into an image → Ideogram V4 + drawing bounding boxes in Comfy. The control here is quite unique. The model uses structured JSON so drawing bounding boxes to get the exact placement works very well. The model only needs 12 steps (turbo), so iterating with different seeds + very impressive text rendering capability leads me to say this is a state of the art open source image model right now. Using the 'Ideogram 4 Prompt Builder' node by Kijai.

rob - comfyui

25,841 Aufrufe • vor 3 Monaten

This is crazy. It reminds me of 2011. Friday, 26 August 2011. Last day of Census training at IUM in town. Gazza's wife, pregnant at that time, was our Supervisor. Everybody left except me and 3/4 ladies. She asked that I help her carry boxes to a car outside. I carry 3 heavy boxes, one on top of the other. I get to the street and there's only a white KIA sedan in parallel parking with Gazza inside. I walked to the car, standing outside the front passenger side with boxes, talking to him. He looks at me and continues operating on his phone. I leave him alone. He doesn't know me, so I get it. I kept standing and waiting for the wife who was carrying her bag and 2 more lighter boxes. The wife comes. The guy opens the boot and remains seated. The wife puts down her boxes, opens the boot and one by one takes off 2 of the 3 boxes I was carrying , loading them into the boot. We loaded hers, she thanked me, got in the car, and they drove off. Maybe that's just how Gazza acts/acted back then - unresponsive.
4:31

This is crazy. It reminds me of 2011. Friday, 26 August 2011. Last day of Census training at IUM in town. Gazza's wife, pregnant at that time, was our Supervisor. Everybody left except me and 3/4 ladies. She asked that I help her carry boxes to a car outside. I carry 3 heavy boxes, one on top of the other. I get to the street and there's only a white KIA sedan in parallel parking with Gazza inside. I walked to the car, standing outside the front passenger side with boxes, talking to him. He looks at me and continues operating on his phone. I leave him alone. He doesn't know me, so I get it. I kept standing and waiting for the wife who was carrying her bag and 2 more lighter boxes. The wife comes. The guy opens the boot and remains seated. The wife puts down her boxes, opens the boot and one by one takes off 2 of the 3 boxes I was carrying , loading them into the boot. We loaded hers, she thanked me, got in the car, and they drove off. Maybe that's just how Gazza acts/acted back then - unresponsive.

Kayilula

13,187 Aufrufe • vor 3 Monaten

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.
5:11

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

AK

83,681 Aufrufe • vor 3 Jahren

AmiGoonies for the Amiga AGA (by Marlox/2-Bit Combo/Amaweks) has a new and comprehensive update, looking great with new scenes and enemies. It's a reimagining of the Konami game (not a port), mostly based on the MSX version, but using Amiga's features such as per-pixel scrolling, parallax and zero "sprite flicker" (mostly blitter objects, to be precise).
1:00

AmiGoonies for the Amiga AGA (by Marlox/2-Bit Combo/Amaweks) has a new and comprehensive update, looking great with new scenes and enemies. It's a reimagining of the Konami game (not a port), mostly based on the MSX version, but using Amiga's features such as per-pixel scrolling, parallax and zero "sprite flicker" (mostly blitter objects, to be precise).

Dante retro dev 💾

20,599 Aufrufe • vor 3 Monaten

I finished a 2 minute 30 second short film using only AI tools inside invideo. I just structured storytelling, precise prompting, and relentless iteration and documented the entire process step by step. I used... - Seedance 1.5 Pro for video generation (Best overall) - Kling 2.6 and Kling 3 for advanced motion scenes - Nano Banana Pro for scene generation and editing - ChatGPT for crafting highly controlled cinematic prompts - Image-to-video methodology to maintain continuity If you’re serious about AI creative video creation, this might change how you approach it. Like, REPOST, and comment "Guide" and I'll DM you the complete step by step guide how to generated it. Watch the complete video here... . .
2:25

I finished a 2 minute 30 second short film using only AI tools inside invideo. I just structured storytelling, precise prompting, and relentless iteration and documented the entire process step by step. I used... - Seedance 1.5 Pro for video generation (Best overall) - Kling 2.6 and Kling 3 for advanced motion scenes - Nano Banana Pro for scene generation and editing - ChatGPT for crafting highly controlled cinematic prompts - Image-to-video methodology to maintain continuity If you’re serious about AI creative video creation, this might change how you approach it. Like, REPOST, and comment "Guide" and I'll DM you the complete step by step guide how to generated it. Watch the complete video here... . .

Beginnersblog

24,784 Aufrufe • vor 6 Monaten

In May, we integrated 11 new models spanning image, 3D, audio, video, and multimodal. The highlights: → Krea 2 — style-first image generation, live as a Partner Node on day one. Competes on how the frame looks, not just what's in it → VOID (Netflix) — removes objects and everything they caused: shadows, reflections, physical interactions. Apache 2.0, natively supported → Tripo 3.1 + TripoSplat — one image to a full 3D Gaussian asset, end to end Also live in May: Gemma 4, HidDream-O1-Image, Stable Audio 3, BiRefNet, MoGe, Claude, OpenRouter, Luma UNI-1 Learn more with our blog 👇
0:47

In May, we integrated 11 new models spanning image, 3D, audio, video, and multimodal. The highlights: → Krea 2 — style-first image generation, live as a Partner Node on day one. Competes on how the frame looks, not just what's in it → VOID (Netflix) — removes objects and everything they caused: shadows, reflections, physical interactions. Apache 2.0, natively supported → Tripo 3.1 + TripoSplat — one image to a full 3D Gaussian asset, end to end Also live in May: Gemma 4, HidDream-O1-Image, Stable Audio 3, BiRefNet, MoGe, Claude, OpenRouter, Luma UNI-1 Learn more with our blog 👇

ComfyUI

20,550 Aufrufe • vor 3 Monaten

🚨#BREAKING: A man in Charlotte NC has filmed incredibly disturbing raw meat deliveries to Halal restaurants in the city. On Day 1, it appears raw meat is just stuffed into the back of an extremely dirty SUV without any refrigeration at all. Day 2, raw meat is literally on the floor of a delivery truck, hanging out of the back... hard to believe it's real. Day 3, raw meat is again seen in a random sedan with raw meat in cardboard boxes, again no refrigeration. This is pretty wild and seems extremely unsanitary at the very least...
0:25

🚨#BREAKING: A man in Charlotte NC has filmed incredibly disturbing raw meat deliveries to Halal restaurants in the city. On Day 1, it appears raw meat is just stuffed into the back of an extremely dirty SUV without any refrigeration at all. Day 2, raw meat is literally on the floor of a delivery truck, hanging out of the back... hard to believe it's real. Day 3, raw meat is again seen in a random sedan with raw meat in cardboard boxes, again no refrigeration. This is pretty wild and seems extremely unsanitary at the very least...

Matt Van Swol

89,008 Aufrufe • vor 6 Monaten

This Chinese developer linked two $2,999 NVIDIA DGX Sparks into one box and runs the full Qwen3-235B at home, after dropping his $1,999-a-month cloud bill to zero. He wired 2 small boxes into a single computer, split a giant 235-billion-parameter model in half between them, and serves it across his own network at about 10 tokens a second, with no internet, no cloud, right there on the desk. No data center, no thousand-dollar graphics cards, no monthly cloud bill. Just him, 2 gold boxes the size of a sandwich, one cable between them, and 1 power strip. And here is the whole payoff. He used to pay the cloud $1,999 a month for the same model, and the meter ticked on every request. Now he paid $5,998 once for 2 boxes, they covered their cost in 3 months, and after that he sends as many requests as he wants for free, only electricity. The two Sparks talk over one fast cable, each holds 128GB of memory, and together they carry the whole model, about 73GB loaded per box, with the chip inside pinned near the limit at 96%. Both boxes work as one and keep trading data over the cable, with no cloud in the loop and no single word leaking out. The ready model sits on one local address, and any app on his network calls it as easily as ChatGPT. And here is how he described, in plain words, what this pair of boxes does: "this is a pair of boxes that holds the huge Qwen3-235B model and serves it to one network. the model is split in half, and each box owns its half. parts: // Box 1 (holds the first half of the model and starts the answer fast, the first word appears in under a second) // Box 2 (holds the second half and writes out the rest, about 10 tokens a second) // Cable (connects the 2 boxes and moves data between them on every step, with no lag) // Address (one local address where any app sends its request, like to a cloud model) // Test (a script that runs big prompts through and measures speed and delays) // Monitor (checks temperature, power draw, and load on both boxes every 2 seconds). the model never goes to the cloud. he only steps in when a box runs hotter than 80 degrees or the cable between them starts dropping data." So the system knows exactly what it is, what it is for, and where its limits are. It knows it has to hold the whole huge model across 2 boxes on its own. It knows it has to answer every request locally, with no meter, no limits, and no internet. It knows the human is only needed when a box overheats or the link between them stalls. → The setup runs around the clock on 2 boxes, each pulling under 60 watts → However many requests he sends, the monthly bill is $0, only electricity → The first box starts the answer in under a second → The second writes text at about 10 tokens a second → One request at a time: 838 tokens in 85 seconds, first word in 0.8s → Two requests at once: 697 tokens in 108 seconds, first word in 0.7s → Both boxes sit at 96% load and warm up to 76-78 degrees And only when a chip in a box runs hotter than 80 degrees or the cable between the 2 Sparks drops data does the system call the owner. And when he himself is out on a run or in a coffee shop, he still reaches his own model at home from his phone: sends a big prompt to the local Qwen3-235B, gets the full answer back in under a minute and a half, with no token meter ticking and no limit to hit. Here is what the test shows on his screen during one of the night runs: "one request at a time: 838 tokens in 84.9 seconds, first word in 0.8s, then 0.1s per token." "two requests at once: 697 tokens in 107.6 seconds, first word in 0.7s, then 0.15s per token." "Box 1: chip at 96% load, 76 degrees, 56 watts, 73GB used in memory." "Box 2: chip at 96% load, 78 degrees, 56 watts, the Qwen3-235B model fully loaded." And while everyone around is paying for AI by the month and bumping into limits, his top-tier model just sits on the desk and works as much as he wants: his own little power plant instead of a forever meter. He has no server rack of his own and no cloud account behind it. Just 2 DGX Spark boxes on a desk, one model split in half between them, one local address, and a folder of prompts next to it. Out of everything I have seen this year, this is the cleanest way to stop paying for AI: $5,998 of hardware on the desk once, $0 a month to the cloud, unlimited forever, and between them 2 gold boxes, 1 cable, and the full Qwen3-235B answering at home with no internet.
1:16

This Chinese developer linked two $2,999 NVIDIA DGX Sparks into one box and runs the full Qwen3-235B at home, after dropping his $1,999-a-month cloud bill to zero. He wired 2 small boxes into a single computer, split a giant 235-billion-parameter model in half between them, and serves it across his own network at about 10 tokens a second, with no internet, no cloud, right there on the desk. No data center, no thousand-dollar graphics cards, no monthly cloud bill. Just him, 2 gold boxes the size of a sandwich, one cable between them, and 1 power strip. And here is the whole payoff. He used to pay the cloud $1,999 a month for the same model, and the meter ticked on every request. Now he paid $5,998 once for 2 boxes, they covered their cost in 3 months, and after that he sends as many requests as he wants for free, only electricity. The two Sparks talk over one fast cable, each holds 128GB of memory, and together they carry the whole model, about 73GB loaded per box, with the chip inside pinned near the limit at 96%. Both boxes work as one and keep trading data over the cable, with no cloud in the loop and no single word leaking out. The ready model sits on one local address, and any app on his network calls it as easily as ChatGPT. And here is how he described, in plain words, what this pair of boxes does: "this is a pair of boxes that holds the huge Qwen3-235B model and serves it to one network. the model is split in half, and each box owns its half. parts: // Box 1 (holds the first half of the model and starts the answer fast, the first word appears in under a second) // Box 2 (holds the second half and writes out the rest, about 10 tokens a second) // Cable (connects the 2 boxes and moves data between them on every step, with no lag) // Address (one local address where any app sends its request, like to a cloud model) // Test (a script that runs big prompts through and measures speed and delays) // Monitor (checks temperature, power draw, and load on both boxes every 2 seconds). the model never goes to the cloud. he only steps in when a box runs hotter than 80 degrees or the cable between them starts dropping data." So the system knows exactly what it is, what it is for, and where its limits are. It knows it has to hold the whole huge model across 2 boxes on its own. It knows it has to answer every request locally, with no meter, no limits, and no internet. It knows the human is only needed when a box overheats or the link between them stalls. → The setup runs around the clock on 2 boxes, each pulling under 60 watts → However many requests he sends, the monthly bill is $0, only electricity → The first box starts the answer in under a second → The second writes text at about 10 tokens a second → One request at a time: 838 tokens in 85 seconds, first word in 0.8s → Two requests at once: 697 tokens in 108 seconds, first word in 0.7s → Both boxes sit at 96% load and warm up to 76-78 degrees And only when a chip in a box runs hotter than 80 degrees or the cable between the 2 Sparks drops data does the system call the owner. And when he himself is out on a run or in a coffee shop, he still reaches his own model at home from his phone: sends a big prompt to the local Qwen3-235B, gets the full answer back in under a minute and a half, with no token meter ticking and no limit to hit. Here is what the test shows on his screen during one of the night runs: "one request at a time: 838 tokens in 84.9 seconds, first word in 0.8s, then 0.1s per token." "two requests at once: 697 tokens in 107.6 seconds, first word in 0.7s, then 0.15s per token." "Box 1: chip at 96% load, 76 degrees, 56 watts, 73GB used in memory." "Box 2: chip at 96% load, 78 degrees, 56 watts, the Qwen3-235B model fully loaded." And while everyone around is paying for AI by the month and bumping into limits, his top-tier model just sits on the desk and works as much as he wants: his own little power plant instead of a forever meter. He has no server rack of his own and no cloud account behind it. Just 2 DGX Spark boxes on a desk, one model split in half between them, one local address, and a folder of prompts next to it. Out of everything I have seen this year, this is the cleanest way to stop paying for AI: $5,998 of hardware on the desk once, $0 a month to the cloud, unlimited forever, and between them 2 gold boxes, 1 cable, and the full Qwen3-235B answering at home with no internet.

Blaze

93,871 Aufrufe • vor 3 Monaten

Meta announces Movie Gen A Cast of Media Foundation Models We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user’s image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, corresponding to a generated video of 16 seconds at 16 frames-per-second. We show multiple technical innovations and simplifications on the architecture, latent spaces, training objectives and recipes, data curation, evaluation protocols, parallelization techniques, and inference optimizations that allow us to reap the benefits of scaling pre-training data, model size, and training compute for training large scale media generation models. We hope this paper helps the research community to accelerate progress and innovation in media generation models
0:30

Meta announces Movie Gen A Cast of Media Foundation Models We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user’s image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, corresponding to a generated video of 16 seconds at 16 frames-per-second. We show multiple technical innovations and simplifications on the architecture, latent spaces, training objectives and recipes, data curation, evaluation protocols, parallelization techniques, and inference optimizations that allow us to reap the benefits of scaling pre-training data, model size, and training compute for training large scale media generation models. We hope this paper helps the research community to accelerate progress and innovation in media generation models

AK

62,719 Aufrufe • vor 2 Jahren

"Please fix Markdown tables!" Okay: text-only, wrapping, columnar selection, proper border conjunctions, fill full width, in opencode beta now. "What took so long?" Here's a writeup: OpenTUI uses yoga layout and has elements called Renderables. Boxes with borders, plain text, code with tree-sitter backed highlighting and other primitives. Organised in a tree structure resembling somewhat of a DOM. Approaching a table naively, given the primitives are there, one would think to just stack box and text elements the right way in a flex-box layout to visually represent a table. Boxes support borders. Problem solved. This is what an LLM would one-shot in a working state, given OpenTUI's API surface. Ignoring the fact that just using box local borders don't handle border conjunctions properly. Benchmarking something like that quickly shows that instantiating an average table takes >70ms and incremental updates become expensive. Hugely due to yoga-layout via wasm having a painful price on yoga API calls. The whole ordeal becomes memory hungry, because a Text element handles more than just plain text. A simple 4x6 table needs a Box and Text per cell, ending up with 48 heavy nodes that yoga must lay out. "But that's just OpenTUI being slow" - you might say. Yes, but no. Yoga should be integrated in the zig native binary core of OpenTUI. It is on the roadmap to do so, which will speed up render passes by 2-5x. Yoga-layout has an open PR to support CSS Grids, which would greatly ease building something like a table. We will use that for fully laid out tables when it gets there. Below the typescript core level Renderables, there are lower level primitives like TextBuffers and TextBufferViews, bound via FFI and completely handled in Zig. I was stuck expecting a table primitive to handle a full layout like a table in the browser does. For Markdown all we need is a text-only table. So we had to come up with a better idea, something that is feasible now. A table layout is pretty straight forward. No need to have yoga deal with that. Using TextBufferViews for cells directly gives lower level control and eliminates some overhead that Boxes and Text renderables have. A simple native method to draw a grid with proper conjunctions is a nice library method. It will surely be used for other cases, so that's what we added. Using this simplified approach we were able to bring down initial instantiation to <1ms, more than 70x improvement. With a far smaller memory footprint. Given all the low level primitives are known and implementing a text-only table like this is possible, Codex was of great help to carve out the PoC, setup the benchmarks and tests. That's only a fraction of what was needed though. The table needs options to span the full available width, render different border styles, show/hide borders, padding, selection etc. So many iterations later OpenTUI now has a text-only, performant and relatively cheap TextTable that we can leverage to render Markdown tables in a streaming/incremental manner. Efficiently and properly.
0:37

"Please fix Markdown tables!" Okay: text-only, wrapping, columnar selection, proper border conjunctions, fill full width, in opencode beta now. "What took so long?" Here's a writeup: OpenTUI uses yoga layout and has elements called Renderables. Boxes with borders, plain text, code with tree-sitter backed highlighting and other primitives. Organised in a tree structure resembling somewhat of a DOM. Approaching a table naively, given the primitives are there, one would think to just stack box and text elements the right way in a flex-box layout to visually represent a table. Boxes support borders. Problem solved. This is what an LLM would one-shot in a working state, given OpenTUI's API surface. Ignoring the fact that just using box local borders don't handle border conjunctions properly. Benchmarking something like that quickly shows that instantiating an average table takes >70ms and incremental updates become expensive. Hugely due to yoga-layout via wasm having a painful price on yoga API calls. The whole ordeal becomes memory hungry, because a Text element handles more than just plain text. A simple 4x6 table needs a Box and Text per cell, ending up with 48 heavy nodes that yoga must lay out. "But that's just OpenTUI being slow" - you might say. Yes, but no. Yoga should be integrated in the zig native binary core of OpenTUI. It is on the roadmap to do so, which will speed up render passes by 2-5x. Yoga-layout has an open PR to support CSS Grids, which would greatly ease building something like a table. We will use that for fully laid out tables when it gets there. Below the typescript core level Renderables, there are lower level primitives like TextBuffers and TextBufferViews, bound via FFI and completely handled in Zig. I was stuck expecting a table primitive to handle a full layout like a table in the browser does. For Markdown all we need is a text-only table. So we had to come up with a better idea, something that is feasible now. A table layout is pretty straight forward. No need to have yoga deal with that. Using TextBufferViews for cells directly gives lower level control and eliminates some overhead that Boxes and Text renderables have. A simple native method to draw a grid with proper conjunctions is a nice library method. It will surely be used for other cases, so that's what we added. Using this simplified approach we were able to bring down initial instantiation to <1ms, more than 70x improvement. With a far smaller memory footprint. Given all the low level primitives are known and implementing a text-only table like this is possible, Codex was of great help to carve out the PoC, setup the benchmarks and tests. That's only a fraction of what was needed though. The table needs options to span the full available width, render different border styles, show/hide borders, padding, selection etc. So many iterations later OpenTUI now has a text-only, performant and relatively cheap TextTable that we can leverage to render Markdown tables in a streaming/incremental manner. Efficiently and properly.

kmdr

208,680 Aufrufe • vor 7 Monaten

The ARTIC FROST drop just COOKED Jack Smith. Jack Smith's plan was to throw as many Trump supporters in prison as possible. From officials in government, to the voters. They literally tapped and spied on Alex Jones's cellphone, text messages, and everything else under the sun, all without a warrant. Alex Jones and Steve Bannon were the only 2 journalists on the list of over 160 Republicans in Trump's circle. cc: Alex Jones
5:09

The ARTIC FROST drop just COOKED Jack Smith. Jack Smith's plan was to throw as many Trump supporters in prison as possible. From officials in government, to the voters. They literally tapped and spied on Alex Jones's cellphone, text messages, and everything else under the sun, all without a warrant. Alex Jones and Steve Bannon were the only 2 journalists on the list of over 160 Republicans in Trump's circle. cc: Alex Jones

The SCIF

105,743 Aufrufe • vor 10 Monaten

I've been a proponent of the idea of combining 3d and generative ai for a long time - as a way to get the best of both worlds: The precision and control of 3d - the detail, realism, lighting and speed of generative models. Here's another example of that idea, realized through a procedural system - entirely vibe-coded with Fable. Inspired by a photograph I took of an old tower in a town in southern France. In the first part of the video I'm using Krea AI's realtime model - later examples show how Nano Banana 2 can be used to take 3d stills and transform them to pretty much anything. What do you think of workflows like this compared to purely generating video or images from text, image or video input?
0:34

I've been a proponent of the idea of combining 3d and generative ai for a long time - as a way to get the best of both worlds: The precision and control of 3d - the detail, realism, lighting and speed of generative models. Here's another example of that idea, realized through a procedural system - entirely vibe-coded with Fable. Inspired by a photograph I took of an old tower in a town in southern France. In the first part of the video I'm using Krea AI's realtime model - later examples show how Nano Banana 2 can be used to take 3d stills and transform them to pretty much anything. What do you think of workflows like this compared to purely generating video or images from text, image or video input?

Martin Nebelong

20,265 Aufrufe • vor 1 Monat

So now we know what was happening in Al Abbad Israeli military base then. This is one of the most important Israeli bases on the entire border line, and it is a great relief to see that Hezbollah was able to operate offensive fpvs in an extremely effective precise targeting campaign like this in the eastern sector, where most of the enemy offensive was focused in the last 2 months. We never witnessed this before, and the Israeli enemy soldiers were definitely correct when they described the situation on the frontline as a hell on earth.
2:11

So now we know what was happening in Al Abbad Israeli military base then. This is one of the most important Israeli bases on the entire border line, and it is a great relief to see that Hezbollah was able to operate offensive fpvs in an extremely effective precise targeting campaign like this in the eastern sector, where most of the enemy offensive was focused in the last 2 months. We never witnessed this before, and the Israeli enemy soldiers were definitely correct when they described the situation on the frontline as a hell on earth.

Hadi Hoteit | هادي حطيط

43,847 Aufrufe • vor 4 Monaten

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:
1:39

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

Tencent Hy

89,392 Aufrufe • vor 1 Jahr

1/ 4.🚧🛠️SWR Help and GWR are reminded that there are several line closures taking place over the October half-term. We're using the time to deliver a bumper package of investment to improve the reliability and resilience of the railway and give passengers more reliable journeys. Here's a reminder of the main closures and key works 🧵👇: #Guildford to #Havant line closure (Saturday 25 Oct – Sunday 2 Nov) 🚦 As part of the #Portsmouth Direct Line Upgrades, we're switching on a brand new signalling system. 90 new signals, 9 upgraded crossings, and transfer of signalling control to #Basingstoke Rail Operating Centre. 🔔As the line goes digital, the final bell has rung at #Farncombe, #Petersfield and #Haslemere signal boxes. An emotional moment for all those who have worked on this line and in the signal boxes over the years 🥹. The final bell at Petersfield signal box in the video below.
0:37

1/ 4.🚧🛠️SWR Help and GWR are reminded that there are several line closures taking place over the October half-term. We're using the time to deliver a bumper package of investment to improve the reliability and resilience of the railway and give passengers more reliable journeys. Here's a reminder of the main closures and key works 🧵👇: #Guildford to #Havant line closure (Saturday 25 Oct – Sunday 2 Nov) 🚦 As part of the #Portsmouth Direct Line Upgrades, we're switching on a brand new signalling system. 90 new signals, 9 upgraded crossings, and transfer of signalling control to #Basingstoke Rail Operating Centre. 🔔As the line goes digital, the final bell has rung at #Farncombe, #Petersfield and #Haslemere signal boxes. An emotional moment for all those who have worked on this line and in the signal boxes over the years 🥹. The final bell at Petersfield signal box in the video below.

Network Rail Wessex

33,169 Aufrufe • vor 11 Monaten

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.
0:21

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.

AK

126,635 Aufrufe • vor 2 Jahren