Alternatives
Products that do what LTXV 13B Distilled – Generate 5s Videos in Under 10s does
Hey HN, after our 13B release we've been working on a faster version of our open-source video model and we're excited to share it. We started with a 13B base model that already had competitive generation speeds (e.g. 55s for a 5s video on an H100 — faster than any other model out there). But we wanted to push it further to allow everyone to quickly iterate over their video generations. So we built a distilled version focused on speed without sacrificing temporal or spatial coherence. With the Distilled model, you can now generate 5-second 720p videos in about 9.5 seconds on an H100, and…
- 1
- 2
- 3
- 4TT
Writeup (includes good/bad sample generations): https://www.linum.ai/field-notes/launch-linum-v2 We're Sahil and Manu, two brothers who spent the last 2 years training text-to-video models from scratch. Today we're releasing them under Apache 2.0. These are 2B param models capable of generating 2-5 seconds of footage at either 360p or 720p. In terms of model size, the closest comparison is Alibaba's Wan 2.1 1.3B. From our testing, we get significantly better motion capture and aesthetics. We're not claiming to have reached the frontier. For us, this is a stepping…
Jan 2026 · huggingface.co
- 5DD
We recently used DeepSeek V4 Flash as a teacher for finance tasks with GPT-OSS-120B. Distillation works well on this problem. At a constrained 8k token budget, our self-distilled 120B scores 83.61% on FinanceReasoning, above Kimi K3 (81.93%) and Inkling (65.13%). We released the 20B open weights. With V4 as the teacher though, we realized it would be timely to measure if the censorship characteristic of it transferred to the distilled version of the base model. tl;dr it didn't, the teacher answered politically sensitive questions 7 SDs differently than expected, but the distilled model's…
Jul 2026 · ctgt.ai
- 6
- 7IM
Hey HN, I've been working on this side project for the past month. It generates a step-by-step tutorial guide for YouTube videos that you can follow along without watching long videos. Best suited for tutorial videos but can work for other videos aswell. No BS. Just straight to the point. The guides are generated from pure transcript so you don't have to worry about it being AI. It's my first project as a total beginner. Something I had to do inorder to get out of tutorial hell. Please let me know if you have any suggestions or if you face any problems or bugs. I would try to fix them to the…
2024 · stepify.tech
- 8LS
Hey HN, this is Lina, Andrew, and Sidney from Lemon Slice. We’ve trained a custom diffusion transformer (DiT) model that achieves video streaming at 25fps and wrapped it into a demo that allows anyone to turn a photo into a real-time, talking avatar. Here’s an example conversation from co-founder Andrew: https://www.youtube.com/watch?v=CeYp5xQMFZY. Try it for yourself at: https://lemonslice.com/live. (Btw, we used to be called Infinity AI and did a Show HN under that name last year: https://news.ycombinator.com/item?id=41467704.) Unlike existing…
2025
- 9RQ
Sep 2025 · github.com
- 10AT
LTX-2 is an open-source diffusion model that combines video and audio. Visually it's not at the level of Seedance 2.0, Veo 3.1, or Sora 2, but it’s open-weights, so anyone can play with it. I wanted to see how good it is at generating video from just audio. Off-the-shelf, it's not very good, but I found that if you run the audio through Gemini to generate a prompt, then feed that into LTX-2, in addition to the audio, the output matches the audio much more often. Foley sounds work particularly well, and one fun use case is uploading audio of yourself to see what AI thinks you look like.…
Mar 2026 · magichour.ai
- 11
- 12RT
I ported Microsoft's TRELLIS.2 (4B parameter image-to-3D model) to run on Apple Silicon via PyTorch MPS. The original requires CUDA with flash_attn, nvdiffrast, and custom sparse convolution kernels: none of which work on Mac. I replaced the CUDA-specific ops with pure-PyTorch alternatives: a gather-scatter sparse 3D convolution, SDPA attention for sparse transformers, and a Python-based mesh extraction replacing CUDA hashmap operations. Total changes are a few hundred lines across 9 files. Generates ~400K vertex meshes from single photos in about 3.5 minutes on M4 Pro (24GB). Not as fast as…
Apr 2026 · github.com
- 13
- 14WM
Try it out! https://glhf.chat/ Hey HN! We’ve been working for the past few months on a website to let you easily run (almost) any open-source LLM on autoscaling GPU clusters. It’s free for now while we figure out how to price it, but we expect to be cheaper than most GPU offerings since we can run the models multi-tenant. Unlike Together AI, Fireworks, etc, we’ll run any model that the open-source vLLM project supports: we don’t have a hardcoded list. If you want a specific model or finetune, you don’t have to ask us for it: you can just paste the Hugging Face link in and…
2024 · glhf.chat
- 15
- 16FT
Aug 2026 · github.com
- 17
- 18
- 19LI
The model has 3B active parameters. We put the code, homepage, paper and model links here: - Code: https://github.com/bytedance/Lance - Homepage: https://lance-project.github.io/ - Paper: https://arxiv.org/abs/2605.18678 - Model: https://huggingface.co/bytedance-research/Lance p.s. Lance is a research project, not a polished product. The model was trained using fewer than 128 GPUs.
May 2026 · github.com
- 20HS
I saw a tweet that tinygrad is so good that you could make a graphics library that wraps tg. So I’ve been hacking on a gtinygrad, and honestly it convinced me it could be used for legit research. The JIT + tensor model ends up being a really nice way to express light transport all in simple python, so I reimplemented some new research papers from SIGGRAPH like REstir PG and SZ and it just works. instead of complicated cpp its just a 200 LOC of python.
Jan 2026 · github.com
- 21UA
Hi HN! I've got the barebones of a service running on top of Stable Diffusion XL. I can cheaply run image generations at 1024x1024. And of course there's a limit to how fast I can generate them given the request queue and limited GPUs, but the service is cheap enough that I'm happy to run it out of pocket for now. Let me know your thoughts, I hope you enjoy the service!
2023 · unstock.ai
- 22H4
Hi HN! We're proud to share Hotshot, a large-scale diffusion transformer model for text-to-video generation that we built with just a 4-person team. You can try it today in beta at https://hotshot.co, with 2 free generations per day. The model generates 5 seconds of 720p video from text prompts. It excels at prompt alignment, and consistency. It also excels at generating people, animals, and nature. In blind tests with 100 users, Hotshot generations were preferred to Runway ML 60% of the time. Hotshot generations were preferred to Luma 80% of the time. Overall, users preferred…
2024 · hotshot.co
- 23I4
It's our new text-to-image model: a 9.3B single-stream diffusion transformer trained entirely from scratch. We focused heavily on controllability through structured JSON prompts, with strong text rendering, spatial awareness through bounding box guidance, and color palette control. It has the best text rendering of any open-weight model we've tested so far, and the NF4 quantized checkpoint runs on a single 24GB GPU. For more technical details and examples see our blog post: https://ideogram.ai/blog/ideogram-4.0/ We will be happy to answer any questions :)
Jun 2026 · github.com
- 24IO
Hiya! So I've been playing around with having Claude make videos for a bit now even had some success posting the results to TikTok (and setup a whole pipeline so Claude can generate and post autonomously). With the release of Nano Banana 2 Lite, I was curious show fast I could make the generation, so last night I gave it a whirl and got down to around 30s for short-form video. It uses GLM-5.2 fast via Fireworks to generate the scripts and image prompts and, like I said, Nano Banana 2 Lite for the images, gpt-4o-mini-tts for the narration, and ffmpeg to string it all together and add the Ken…
Jul 2026 · instantvideos.org
Ranked by how close each launch is in meaning, then by votes. Refine with a description →