Загрузка видео...

Не удалось загрузить видео

На главную

LTX-2.5 is native in ComfyUI, day zero with the weights Model highlights: → Diffusion Fidelity Rendering - compute allocated by scene complexity, not spread evenly → Diffusion Video Decoder - replaces VAE decoding, sharper faces and legible text → Native multi-shot - one run, multiple connected shots, consistent across...

2,406,572 просмотров • 3 месяцев назад •via X (Twitter)

Комментарии: 17

Фото профиля ComfyUI
ComfyUI3 месяцев назад

Click the link below:

Фото профиля Prince does AI
Prince does AI3 месяцев назад

legible text in video is the part i care about

Фото профиля ComfyUI
ComfyUI3 месяцев назад

That I 100% agree with.

Фото профиля Rob Hoffman (No longer redacted)
Rob Hoffman (No longer redacted)3 месяцев назад

In my meager tests, it's a big speed improvement. Looking forward to giving it a real workout this weekend.

Фото профиля LabMike 3D
LabMike 3D3 месяцев назад

I'm currently testing LTX 2.5 on my RTX 3060 12GB, and it's pretty fast with great quality. Cheers!

Фото профиля 泰多宝
泰多宝3 месяцев назад

The decoder swap is the one that changes what you can ship. A VAE trained on reconstruction loss averages high-frequency detail, and faces and glyphs are made of exactly that — you get texture that looks like text rather than text. A diffusion decoder generates the detail instead of averaging it, which is why it comes out legible. The tradeoff rides along though: legible isn't correct, since it synthesises plausible strokes rather than recovering the encoded ones.

Фото профиля LabMike 3D
LabMike 3D3 месяцев назад

LTX 2.5 on RTX 3060: Impressive Speed & Quality Out of the Box

Фото профиля JSFILMZ
JSFILMZ3 месяцев назад

10 sec max duration in 2026 is wild

Фото профиля smallzero
smallzero3 месяцев назад

I got you! Already created a video showing how to launch inside ComfyUI

Фото профиля Vini
Vini3 месяцев назад

Allocating compute by scene complexity instead of evenly is smart engineering.

Фото профиля Mr Zoulll
Mr Zoulll3 месяцев назад

Mon RTX 5090 l'adore. 🥰

Фото профиля Hao
Hao3 месяцев назад

拿中文语境做了2次实验,跟h3对比…🤦

Фото профиля Nazar
Nazar3 месяцев назад

Replacing VAE decoding is the line people will skim past and shouldn't. Faces and text going soft in the decode has been the tell on every open video model. If that is genuinely fixed, it changes what these are usable for beyond b-roll.

Фото профиля Narine Saw
Narine Saw2 месяцев назад

Ltx lol Mini Max h3 !!!

Фото профиля derrick has started yet another project
derrick has started yet another project3 месяцев назад

No more Israeli models thanks

Фото профиля ReAiLity Labs
ReAiLity Labs3 месяцев назад

Is a new template being pushed out in Comfyui or did the existing ltx templates get updated?

Фото профиля Edgex
Edgex3 месяцев назад

Wow, the Diffusion Fidelity Rendering really changes the game - love how it adapts to scene complexity.

Похожие видео

Auto regressive LLMs are officially on notice. run Gemma 4 26B diffusion gguf with llama.cpp Google just dropped DiffusionGemma-26B, and it completely flips how we generate text. instead of predicting words one by one, it generates 256 tokens in parallel using bi-directional attention. its like stable diffusion, but for language. the model starts with random text "noise" and iteratively refines and self-corrects the entire block in real-time to fix formatting and reasoning errors on the fly. since it’s a Mixture of Experts (MoE) that only activates 3.8B parameters during inference, it fits perfectly on consumer hardware. You can run the Q4_K_M quant with an 18GB VRAM budget on a single RTX 3090 or RTX 4090 with exceptional throughput. Tested on Ubuntu 22 with CUDA 13.1 using the cutting edge experimental llama.cpp branch. Here is how to compile and run it with the live terminal denoising visualizer: # 1. Clone & check out the experimental PR (#24423) - 1) git clone && cd llama.cpp -git fetch origin 2) pull/24423/head:diffusiongemma && --git checkout diffusiongemma # 2. Build with CUDA support 1) cmake -B build -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=native 2) cmake --build build -j $(nproc) --config Release --target llama-diffusion-cli # 3. Run with live visual denoising (llama.cpp flags) ./build/bin/llama-diffusion-cli \ -m /path/to/diffusiongemma-26B-A4B-it-Q4_K_M.gguf \ -ngl 99 -cnv -n 2048 --diffusion-visual Watch the video below to see the live --diffusion-visual canvas iteratively de noising the prompt output in real time. guide and unsloth's hugging face GGUF model links are in the comments below! Is auto regressive generation officially legacy tech? Let me know what you think.

Alok

52,656 просмотров • 5 месяцев назад