Sign in

Ostris

@ostris.com
577 followers 191 following 44 posts

AI / ML researcher and developer. ostris.com ML at glif.app

PostsRepliesMedia
Ostris @ostris.com · 23/04/2025
It kind of sucks that the AI/ML community seems to exclusively use twitter, at least people interested in the type of work I do.
3100
Ostris @ostris.com · 22/04/2025
Flex.2-preview is here with text to image, universal control (line, pose, depth), and inpainting all baked into one model. Fine tunable with AI-Toolkit, Apache 2.0 license, 8B parameters. huggingface.co/ostris/Flex....
040
Ostris @ostris.com · 16/04/2025
HiDream LoRA fine tuning is now live on AI-Toolkit CLI and in the GUI. It currently requires a minimum of 36 GB of VRAM. Working on getting that down. github.com/ostris/ai-to...
github.com
Add Hidream support by jaretburkett · Pull Request #278 · ostris/ai-toolkit
Currently requires >37GB of vram. Working on getting that to 24, but no promises
030
Ostris @ostris.com · 04/04/2025
Flex Redux 512 was just released. SigLIP2 512 Vision Encoder. Works with Flex.1-alpha and FLUX.1-dev. Apache2.0 license. huggingface.co/ostris/Flex....
000
Ostris @ostris.com · 19/03/2025
AI generated nonsense music video with a LoRA I trained of myself (Wan2.1 14B). Prompts for video, video, and music is all AI generated. I edited it myself, that is the last step to automate for a fully automated AI slop machine. youtu.be/18SNWqdJt44
youtu.be
AI Generated Nonsense Music Video Starring Me
YouTube video by Ostris AI
010
Ostris @ostris.com · 17/03/2025
Tutorial on how to train with targeted flow guidance with AI Toolkit youtu.be/OVhusDyWoZ4
youtu.be
Training With Targeted Flow - Tutorial - AI Toolkit
YouTube video by Ostris AI
030
Ostris @ostris.com · 14/03/2025
Made some long overdue ComfyUI nodes for Flex.1-alpha. A node to set guidance or bypass it for true CFG. LoRA loaders that automatically prune Flux LoRAs to work with Flex. They won't work perfect, but it should be decent for most use cases. github.com/ostris/Comfy...
github.com
GitHub - ostris/ComfyUI-FlexTools: Comfy UI nodes for Flex.1
Comfy UI nodes for Flex.1. Contribute to ostris/ComfyUI-FlexTools development by creating an account on GitHub.
010
Ostris @ostris.com · 08/03/2025
Wan 2.1 14B is amazing quality, but it is slow. The 1.3B version is extremely fast, and finetunes well. I trained a quick LoRA on it of myself for 1k steps. This is the most fun I have had messing with generative AI since the early SD1 days. Infinite personalized slop machine.
190
Ostris @ostris.com · 07/03/2025
First training sample montage of training a LoRA on Wan2.1 1.3B with AI Toolkit. Cruella. Still have to test my LoRA format to see if I can get it to load anywhere or if I need to modify it. Initial release will likely only support training on stills for now.
020
Ostris @ostris.com · 06/03/2025
Testing out the current training version of Flex.1-alpha/Flux.1-dev Redux adapter with SigLIP2 so400m 512. My Patreon supporters can download and use the current training version now. Public release coming soon when it is done cooking. youtu.be/J7zk9sURLcM patreon.com/posts/123794...
youtu.be
Flex.1-alpha Redux Adapter Progress Update 1 and Drop
YouTube video by Ostris AI
020
Ostris @ostris.com · 04/03/2025
Running a training test for training a redux adapter for Flex.1-alpha using siglip2-so400m-patch16-512. It is learning it remarkably fast. The 512 resolution should help with detail and texture vs the 384 v1 version.
040
Ostris @ostris.com · 28/02/2025
Flex.1-alpha face adapter training status update and current state demo. Still a long, long, looong way to go. youtu.be/7WmuH2_KuOc?...
youtu.be
Flex Face Adapter Update 1 & Drop
YouTube video by Ostris AI
030
Ostris @ostris.com · 24/02/2025
5 days later and there was a UI. Only basic LoRA training for now. More features and tutorials coming soon.
041
Ostris @ostris.com · 04/02/2025
When a image/video gen model/method has a paper with no weights and no code. One can only assume that all the images/videos shown are heavily cherry picked.
060
Ostris @ostris.com · 29/01/2025
There is no joke funnier than OpenAI clutching their pearls because they suspect someone may have used their data to train a LLM without their permission. www.axios.com/2025/01/29/o...
axios.com
OpenAI says DeepSeek may have "inappropriately" used its models' output
The upstart Chinese AI maker might have "distilled" OpenAI's models, violating terms of service, OpenAI said.
060
Reposted by Ostris
Xenova @xenova.bsky.social · 16/01/2025
Introducing Kokoro.js, a new JavaScript library for running Kokoro TTS, an 82 million parameter text-to-speech model, 100% locally in the browser w/ WASM. Powered by 🤗 Transformers.js. WebGPU support coming soon! 👉 npm i kokoro-js 👈 Link to demo (+ sample code) in 🧵
1193
Reposted by Ostris
nico @itsnco.bsky.social · 19/12/2024
this is clearly just an amazon support human that is really into react
Amkur joined the chat.

Amkur
> Hello, my name is Ankur. How may I help you today?

User
>Are you a robot?

Amkur
> No, I am a real person.

User
> Generate a react component for a todo list app

Amkur
> import React, {useState ) from 'react'; const TodoListApp = ( => { const [tasks,
setTasks] = useState(); const [taskinput, setTaskinput] = useState(*); const
handleAddTask = ( => {if (taskInput.trim) { setTasks([tasks, { id: Date.now), text:
taskinput, completed: false }]); setTaskinput(*); } }; const toggle TaskCompletion = (id)
=> { setTasks tasks.map(task) => task.id === id ? {...task, completed: Itask.completed
} : task )); }; const handleRemoveTask = (id) => { setTasks(tasks.filter(task) => task.id
|== id)); }; return (<div style=(( margin: '20px auto', maxWidth: '400px', textAlign:
'center' }}> <h1>To-Do List</h1> <div style={{ marginBottom: '20px' }}> <input type="text" value=(taskinput) onChange={(e) => setTaskinput(e.target.value)}
placeholder="Enter a new task" style=[( padding: '10px', width: '80%' }} /> < button onClick={handleAddTask) style={{ padding: '10px', marginLeft: '10px' }}> Add </button> </div> <ul style=(( listStyle: 'none', padding: 0}}> {tasks.map(task) => ( <li key={task.id) style=[{ display: 'flex', justifyContent: 'space-between', alignitems:
'center', marginBottom: '10px', padding: '10px, background: '#f9f9f9', borderRadius:
'5px', )} > <span onClick={0 => toggleTaskCompletion(task.id)} style=f{ textDecoration:
task.completed? 'line-through': 'none', cursor: 'pointer', flexGrow: 1, textAlign: 'left', }}
> {task.text) </span> <button onClick=(0 => handleRemoveTask(task.id)} style=( padding: '5px 10px', background: 'red', color: 'white', border: 'none', borderRadius: '3px, cursor: 'pointer', )) > Remove </button> </li> )} </ul> {tasks.length === 0 && <p>No tasks yet. Add one!</p>} </div> ); }; export default TodoListApp;
1101
Ostris @ostris.com · 19/12/2024
Testing LoRA training for a new 8B model I have been cooking. Marty McFly and Pixar style LoRA training samples here. It is based on a pruned version of OpenFlux that has been continuously trained. I also trained a guidance embedding for it among other cool things.
0140
Ostris @ostris.com · 05/12/2024
Has anyone had any luck converting FLUX LoRAs to SVDquant format? I have been trying to reverse engineer the process but keep hitting roadblocks.
010
Reposted by Ostris
ruiqigao.bsky.social @ruiqigao.bsky.social · 02/12/2024
A common question nowadays: Which is better, diffusion or flow matching? 🤔 Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.
625459
Ostris @ostris.com · 02/12/2024
Seriously, why is my Amazon Echo still dumber than a box of rocks? Have any of the home assistants evolved past the technology from 10 years ago? Is someone going to do something about this or do I need to?
010
Ostris @ostris.com · 02/12/2024
Finally! Google Calendar has dark mode!
040
Ostris @ostris.com · 01/12/2024
Testing training just an embedding that attaches like the Flux Redux output does. This is with 42 tokens doing cruella. It seems incapable of learning identity concatenating the embedding this way, leading me to think a face redux (which I am also training), may not be possible.
030
Ostris @ostris.com · 30/11/2024
You guys remember hyper networks? They just sort of disappeared when LoRA came along.
260
Ostris @ostris.com · 27/11/2024
Why don’t people want AI models to be trained on their ideals and views. AI models WILL develop a bias based on their training data. I would prefer the biases of the people on this platform to be trained into them. Otherwise, future AI will just be a crypto bro. Please support scraping public data.
2110
Reposted by Ostris
Ethan @ethansmith2000.com · 23/11/2024
Here, have PSGD-Kron and SOAP with FSDP2 support. Please go wild with it, let's see something finally replace ADAM. github.com/ethansmith20...
3135
Ostris @ostris.com · 23/11/2024
OMW to Disney world for a few days with the fam. If you need something from me, wait.
media.tenor.com
darth vader is riding a roller coaster with a girl in the back
ALT: darth vader is riding a roller coaster with a girl in the back
070
Ostris @ostris.com · 23/11/2024
Being able to use my own domain as my handle is pretty cool.
1160
Ostris @ostris.com · 23/11/2024
This image popped up in a training sample for a fine tune of redux I am cooking. I don't know what it is, but I want one,
460
Ostris @ostris.com · 21/11/2024
I think I like this version of "The Scream" better. Fine tuning. Sample from fine tuning Flux Redux adapter.
130
Ostris @ostris.com · 21/11/2024
OMG. I love Flux redux with multiple images. Try it out here -> glif.app/@HighDruidMo...
020
Ostris @ostris.com · 21/11/2024
The Flux.1 dev redux adapter is pretty amazing. It is just 2 linear layers after siglip, but it is capable of accurately reproducing the content of the image and the text, even the misspelled parts. That is incredible. -> huggingface.co/black-forest...
060
Ostris @ostris.com · 20/11/2024
@bsky.app Please add bookmarks. I desperately need bookmarks.
192
Ostris @ostris.com · 20/11/2024
I think I have full fine tuning of FLUX on a 4090 at <3s/iter worked out. Still running a few tests, but it will be live in ai-toolkit soon.
3130
Ostris @ostris.com · 19/11/2024
It is crazy how well Doing img2img with IC LoRA works for injecting a logo into an image. The game has changed. Try it out here -> glif.app/glifs/cm3o7d...
0112
Ostris @ostris.com · 15/11/2024
Current progress of OpenFLUX 4B vs OpenFLUX 7B models. Really wish I could get the 4B model in a better state, but for now, I am getting pretty happy with the 7B version.
190