Aivan Monceller
@aivandroid
Followers
154
Following
1K
Media
31
Statuses
865
I share interesting things I find, what I’m learning, and projects I’m trying. Follow me if you like tech, creative stuff, and learning new things. INFJ-T
Sinapore ⇄ Philippines
Joined March 2018
Created a video how to train Flux LoRAs using my convenience script utilizing ai-toolkit on @quickpodio
https://t.co/MvqYVjdVkm
0
1
6
Found a new tool for swapping faces in videos called DreamID-V It lets you take a photo of a face and put it onto a person in a video. The code is open source if you want to take a look.
1
0
0
I can finally put my ChatGPT plan to work!
in opencode v1.1.11 you can now use your ChatGPT Plus/Pro plans in OpenCode /connect to set it up
0
0
0
Ostris is cooking again can't wait for LTX-2 LORA training on AI Toolkit
LTX-2 in AI Toolkit progress: I have model loading, quantizing, ramtorch offloading, and training on images / videos without sound working. Need to finish up sound and add i2v support, but it is coming along. Tested a 2 character LoRAs. <24GB of vram for image only. This is not
0
0
1
llama.cpp for me since day 1
nobody should use ollama btw > slower than llama.cpp on windows > slower than mlx on mac > slop useless wrapper alternatives? > lmstudio > llama.cpp > exllamav2/v3 > vllm > sglang like literally anythingʼs better than ollama lmao
0
0
0
fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA 角度変更、めちゃくちゃ精度高くてすごい Qwen Image Multiple Angles 3D Camera - a Hugging Face Space by multimodalart https://t.co/i4VOra0kbt
77
1K
10K
I use one monitor if I have to focus, multiple if I want to have fun.
@FlorinPop17 Studies prove this btw, multiple monitors are less productive and just distract
0
0
0
new years resolution for all tech companies should be first 3 months no features, all fixes looking at you Windows
118
155
3K
All of your predictions for software engineering and AI are wrong (including this one). We’ll see an explosion of personalized software. I don’t have to learn your complex UX, I can make my own. How that affects professional and enterprise software is yet to be understood.
16
8
101
There are no limits anymore. Anyone can do anything. The only limiting factors are agency and ambition. Never has a college degree, work experience, network, even the accumulation of knowledge been worth less. You can just ship things.
350
721
7K
Currently having a blast learning @huggingface transformers I noticed that model cards usually have Transformers code as usage examples So I tried to figure out how to load a model just using the transformers library without using ollama, lmstudio, or llamacpp Learned how to
2
4
20
Remember when AI text was just gibberish? The jump in text rendering and panel consistency is wild #Gemini3Pro #NanoBanana2
0
0
0
Big news: Replicate is joining Cloudflare. Replicate's going to carry on as a distinct brand, and all that will happen is that it’s going to get way better: it’ll be faster, we’ll have more resources, and it’ll integrate with the rest of Cloudflare’s Developer Platform.
263
168
2K
Faster lint + test = faster AI iteration loops!
Oxlint is crazy fast on a bigger codebase with m4pro Eslint takes 12 seconds Oxlint 66ms This really will change how to write code especially for ai.
9
18
315
coding agents seem to be getting good at the "rewrite this from X to Y", they get you to 95%, and then you spend a little time cleaning up loose ends and all. This feels important because choosing a framework/lib has _always_ been a such a heavy decision.
7
2
57
BOOOOOOOM! CHINA DEEPSEEK DOES IT AGAIN! An entire encyclopedia compressed into a single, high-resolution image! — A mind-blowing breakthrough. DeepSeek-OCR, unleashed an electrifying 3-billion-parameter vision-language model that obliterates the boundaries between text and
347
1K
8K
Higgsfield Sora 2 Stream goes LIVE on YouTube in less than an hour. Learn how viral clips are made, the exact prompts that work, and the playbook to turn Sora 2 into growth + revenue. Join here: https://t.co/BNHacESVhc RT+Reply to get 150 creds in DM.
378
342
596
I unfortunately don't know much about mobile app and desktop software dev so I'm genuinely asking: WHY DO ALL COMPANIES RELEASE iOS/macOS PRODUCTS FIRST/ONLY??? How hard is it to release Android and Windows versions of your product? Recent example is the Sora app, which is
954
67
2K