Social Post Explorers

community
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

social-post-explorers's activity

MonsterMMORPG 
posted an update 2 days ago
view post
Post
1927
I have Compared Kohya vs OneTrainer for FLUX Dev Finetuning / DreamBooth Training

OneTrainer can train FLUX Dev with Text-Encoders unlike Kohya so I wanted to try it.

Unfortunately, the developer doesn't want to add feature to save trained Clip L or T5 XXL as safetensors or merge them into output so basically they are useless without so much extra effort.

I still went ahead and wanted to test EMA training. EMA normally improves quality significantly in SD 1.5 training. With FLUX I have to use CPU for EMA and it was really slow but i wanted to test.

I have tried to replicate Kohya config. The below you will see results. Sadly the quality is nothing sort of. More research has to be made and since we still don't get text-encoder training due to developer decision, I don't see any benefit of using OneTrainer for FLUX training instead of using Koha.

1st image : Kohya best config : https://www.patreon.com/posts/112099700

2nd image : One Trainer Kohya config with EMA update every 1 step

3rd image : One Trainer Kohya config with EMA update every 5 steps

4th image : One Trainer Kohya config

5th image : One Trainer Kohya config but Timestep Shift is 1 instead of 3.1582

I am guessing that Timestep Shift of OneTrainer is not same as Discrete Flow Shift of Kohya

Probably I need to work and do more test and i can improve results but i don't see any reason to do atm. If Clip Training + merging it into safetensors file was working, I was gonna pursue it

These are not cherry pick results all are from 1st test grid

MonsterMMORPG 
posted an update 6 days ago
view post
Post
1663
CogVLM 2 Batch Processing App updated to support RTX 5000 series as well. I have compiled xFormers to make it work. Most Powerful Vision Model that can be used for image captioning. Now works with RTX 5000 series as well including older GPUs like 4000 3000 2000 series. Supports 4-bit quantization as well so it uses minimal amount of VRAM.

App link : https://www.patreon.com/posts/120193330

Check out below screenshots

giux78 
posted an update 7 days ago
view post
Post
3135
This is truly an inspirational story please help us spread the word, @clem , @thomwolf and everyone who supports open source AI.

A few weeks ago, @mmuffo94 and @cittiberto from indigo_ai launched the Chatbot Arena for the Italian language: https://indigo.ai/it/chatbot-arena-italia/.

To our surprise, among the top-ranked models is mii-llm/maestrale-chat-v0.4-beta a carefully fine-tuned version of mistralai/Mistral-7B-v0.1, developed by @efederici and @mferraretto from mii-llm , and released nearly a year ago.

At this very moment, as shown in the screenshot, mii-llm/maestrale-chat-v0.4-beta is ranked 8th right between ChatGPT-4.5 and ChatGPT-4o.

It's likely that for several months, the best Italian speaking LLM has been an open source 7B model created by open source contributors and hardly anyone knew it.
  • 2 replies
·
kshitizkhanal7 
posted an update 8 days ago
wassemgtk 
posted an update 9 days ago
view post
Post
2038
For fun, a new project: SuperTokenizer! A BPE tokenizer trained on C4 to beat GPT-4. Byte-level, A100-powered, and open-source. Messing around with tokens!
https://github.com/wassemgtk/SuperTokenizer
  • 1 reply
·
takarajordan 
posted an update 9 days ago
view post
Post
1838
Takara takes 3rd place in the {tech:munich} AI hackathon with Fudeno!

A little over 2 weeks ago @aldigobbler and I set out to create the largest MultiModal SVG dataset ever created, we succeeded in this and when I was in Munich, Germany I took it one step further and made an entire app with it!

We fine-tuned Mistral Small, made a Next.JS application and blew some minds, taking 3rd place out of over 100 hackers. So cool!

If you want to see the dataset, please see below.

takara-ai/fudeno-instruct-4M
MikeDoes 
posted an update 9 days ago
view post
Post
2756
🚀 We are quite excited to announce the Ai4Privacy Python library! 🎉

pip install ai4privacy to anonymize short english text with OpenPII Masking 500k labels

📊 Day 5/7 of PII Masking 1M announcements complete! ⏰
MikeDoes 
posted an update 10 days ago
MonsterMMORPG 
posted an update 12 days ago
view post
Post
3324
I am doing a workflow research for a company and our Ultimate Image Processing tool is being extremely helpful. You can auto zoom / crop into desired aspect ratio with using prompts (like a shoe) via SAM2 that we have in our batch processing app.

Gradio based App link : https://www.patreon.com/posts/120352012


MikeDoes 
posted an update 13 days ago
view post
Post
1705
📊 99%+ PII Masking Precision in English Straight to Your Browser! 🚀

ai4privacy/general-english-anonymiser-openpii-500k

Hard Facts:
🖥️ Runs in-browser—blazing fast, no server latency
👐 Open-source, MIT-licensed (even for commercial use)
📈 Full metrics on Hugging Face dataset and model pages

Day 3 out 7 of PII-Masking-1M Announcements Complete!
*Accuracies reported from the new OpenPII-500k dataset

#DataPrivacy #AI #OpenSource
sharpenb 
posted an update 14 days ago
view post
Post
3061
We open-sourced the pruna package that can be easily installed with pip install pruna :) It allows to easily ccompress and evaluate AI models including transformers and diffusers.

- Github repo: https://github.com/PrunaAI/pruna
- Documentation: https://docs.pruna.ai/en/stable/index.html

With open-sourcing, people can now inspect and contribute to the open code. Beyond the code, we provide detailed readme, tutorials, benchmarks, and documentation to make transparent compression, evaluation, and saving/loading/serving of AI models.

Happy to share it with you and always interested in collecting your feedback :)
  • 1 reply
·
MonsterMMORPG 
posted an update 14 days ago
view post
Post
1399
Extending Wan 2.1 generated video - First 14b 720p text to video, then using last frame automatically to to generate a video with 14b 720p image to video - with RIFE 32 FPS 10 second 1280x720p video

Our app has this fully automated : https://www.patreon.com/posts/123105403

Here how it works image : https://ibb.co/b582z3R6

Workflow is easy

Use your favorite app to generate initial video.

Get last frame

Give last frame to image to video model - with matching model and resolution

Generate

And merge

Then use MMAudio to add sound

I made it automated in my Wan 2.1 app but can be made with ComfyUI easily as well . I can extend as many as times i want :)

Here initial video

Prompt: Close-up shot of a Roman gladiator, wearing a leather loincloth and armored gloves, standing confidently with a determined expression, holding a sword and shield. The lighting highlights his muscular build and the textures of his worn armor.

Negative Prompt: Overexposure, static, blurred details, subtitles, paintings, pictures, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, mutilated, redundant fingers, poorly painted hands, poorly painted faces, deformed, disfigured, deformed limbs, fused fingers, cluttered background, three legs, a lot of people in the background, upside down

Used Model: WAN 2.1 14B Text-to-Video

Number of Inference Steps: 20

CFG Scale: 6

Sigma Shift: 10

Seed: 224866642

Number of Frames: 81

Denoising Strength: N/A

LoRA Model: None

TeaCache Enabled: True

TeaCache L1 Threshold: 0.15

TeaCache Model ID: Wan2.1-T2V-14B

Precision: BF16

Auto Crop: Enabled

Final Resolution: 1280x720

Generation Duration: 770.66 seconds



·
MikeDoes 
posted an update 15 days ago
view post
Post
2085
#PII Masking Tech that does not **** around!

We are happy to release the OpenPII English Anonymiser —the most powerful open-source tool for redacting sensitive info from English text.

Fine-tuned Modernbert on 5.7 million+ PII examples, it’s clocking 99%+ accuracy across emails, dates, social numbers, and more!

Why it’s a big deal:
✅ Top-tier precision: 100% for passport numbers, 99.96% for emails*.
✅ Totally free: MIT license for personal or commercial use.
✅ No secrets: Full metrics shared on Hugging Face.

#AI #OpenSource #DataSecurity @huggingface

Day 2 out 7 of PII-Masking-1M Announcements Complete!

*Accuracies reported from the new OpenPII-500k dataset

ai4privacy/llama-ai4privacy-english-anonymiser-openpii
MonsterMMORPG 
posted an update 15 days ago
view post
Post
812
MMAudio Full Tutorial - Open Source AI Audio Generator for Videos - Useful for Games and AI Videos

Full tutorial link : https://youtu.be/504f8S4MLTw

GitHub repo : https://github.com/hkchengrex/MMAudio

MMAudio is the currently state of the art (SOTA) open source free to use AI model to generate sounds for videos, images and text prompts. It is so amazing and high quality and extremely useful to generate sound effects for your AI videos, game assets, or any project where you need specific or free sound effects. In this step by step tutorial I will show you how to install and use this amazing model on your Windows computer with 1-click installation and extremely easy to use Gradio App. My app and installation supports RTX 5000 series GPUs as well as older GPUs. Moreover, I am sharing scripts to 1-click install on Cloud services such as RunPod, Massed Compute and a free Kaggle account notebook. Enjoy.

🔗 Full Instructions, Configs, Installers, Information and Links Shared Post (the one used in the tutorial) ⤵️
▶️ https://www.patreon.com/posts/click-to-open-post-used-in-tutorial-117990364

🔗 Mandatory Requirements Tutorial⤵️
▶️ https://youtu.be/DrhUHnYfwC0

Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

MMAudio generates synchronized audio given video and/or text inputs. Our key innovation is multimodal joint training which allows training on a wide range of audio-visual and audio-text datasets. Moreover, a synchronization module aligns the generated audio with the video frames.

MikeDoes 
posted an update 17 days ago
view post
Post
2687
🚀 Ai4Privacy Team is excited to unveil PII-Masking-1M, our most significant release yet! 🎉

This publication series 📦 includes datasets 📊, models 🤖, and applications ⚙️ to advance PII masking with AI systems 🛡️

Starting on Monday with daily posts at 7 PM CET ⏰
MonsterMMORPG 
posted an update 17 days ago
view post
Post
1032
Prepared presets for Wan 2.1 for every model and GPU with modelscope / DiffSynth-Studio - Works with maximum speed as long as you are not using more than 2 GB VRAM - Compared BF16 vs FP8 as well

Our app tutorial main : https://youtu.be/hnAhveNy-8s

2nd tutorial : https://youtu.be/ueMrzmbdWBg

Our App : https://www.patreon.com/posts/click-to-open-post-used-in-tutorial-123105403

Also our App now has fully updated presets for every GPU both for BF16 and FP8 precision
giux78 
posted an update 17 days ago
view post
Post
2841
@ mii-llm with @efederici @mferraretto @FinancialSupport and @DeepMount00 we just released #Propaganda a framework designed to evaluate and train LLMs on political opinions and bias. We aim to analyze both open-source and closed-source LLMs to understand the political positions and biases expressed in their outputs. Moreover we provide a set of recipes to enforce political positions into the models by creating ad hoc curated datasets and by applying fine tuning techniques. By releasing our work in the open, we hope to foster contributions: https://github.com/mii-llm/propaganda

This framework offers opportunities for expansion in various directions and could become the standard reference for evaluating LLMs on political topics, particularly those that influence public opinion.
reddgr 
posted an update 18 days ago
MonsterMMORPG 
posted an update 19 days ago