- Видео 161
- Просмотров 140 410
Альберт Иванов
Добавлен 10 окт 2012
Infini-Megrez-Omni(analysis of image, text, and audio modalities) on rtx 3050 (cuda) test
github.com/infinigence/Infini-Megrez-Omni
- model also can take audio as a prompt
- can describe audio fragment (english)
- supports chatting about the image
- ocr works good (can extract numbers from the price)
- handwritten ocr works worse
- inference time on gpu (image description) - 32 sec
- model also can take audio as a prompt
- can describe audio fragment (english)
- supports chatting about the image
- ocr works good (can extract numbers from the price)
- handwritten ocr works worse
- inference time on gpu (image description) - 32 sec
Просмотров: 11
Видео
voice cloning (rus-to-rus) with fish speech 1.5 on raspberry pi5
Просмотров 5714 дней назад
speech.fish.audio/#windows-setup выводы: - генерация пары предложений занимает до 5 минут - результат клонирования достойный, но не всегда удачный - иногда плохо справляется с ударениями в словах и интонацией - на данный момент пока нет onnx реализации
show network stat with netplot on raspberry pi5
Просмотров 1414 дней назад
find out what programs sends to net on raspberry pi. github.com/fedeb95/netplot *package has broken install so to start it working just copy-paste files to main dir and change imports in netplot.py: see fork - github.com/zoldaten/netplot
yolov8n.onnx vs yolov8.rknn on luckfox 3566 speed test on 1 image
Просмотров 2821 день назад
github.com/airockchip/rknn_model_zoo
yolov5m.rknn test on luckfox 3566
Просмотров 37Месяц назад
luckfox 3566 has NPU with 0.8 TOPS - so to use ones need do conversion: .pt - .onnx - .rknn. models from - github.com/Qengineering/YoloV5-NPU ./YoloV5_NPU rk3566/yolov5s-240-240_rk3566.rknn small-vehicles.jpg yolov5m.rknn - 5 fps ! very good keep in mind yolov5s.pt gives only 0,3 FPS.
sana 1024 × 1024 (local image generation) test on 3090 rtx ubuntu
Просмотров 20Месяц назад
github.com/NVlabs/Sana prompt = 'a stunning portrait of a woman with flawless skin, her face adorned with intricate floral patterns painted in sort pastel hues,\ gazing thoughtfully while standing in a vast lavender field swaying gently in the breeze;ultra-realistic details,natural lighting?and a dreamy,\ blurred background' выводы: - быстрая скорость (4 сек), заметно быстрее flux schnell - кач...
yolov8 cpp ncnn with vulkan inference on raspberry pi4b - very slow
Просмотров 41Месяц назад
1.convert yolov8n.onnx to ncnn format: pnnx yolov8n.onnx inputshape=[1,3,640,640] yolov8n.bin and yolov8n.param - ready for inference. 2.start cpp inference with ncnn: ./yolov8 image.jpg
vulkan on raspberry pi 4b bullseye aarch64 - samples tests
Просмотров 49Месяц назад
how to install vulkan on bullseye aarch64: qengineering.eu/install-vulkan-on-raspberry-pi.html but missed some libs on link above. additional libs should be installed: sascha willems wont work. may be it need sdk to be installed. so use this examples: github.com/KhronosGroup/Vulkan-Samples/blob/main/docs/build.adoc#linux
yolov11.mnn vs yolov11.onnx speed comparison on raspberry pi4b
Просмотров 93Месяц назад
export to mnn, onnx - docs.ultralytics.com/integrations/mnn/#how-do-i-export-ultralytics-yolo11-models-to-mnn-format mnn install on raspberry - qengineering.eu/install-mnn-on-raspberry-pi-4.html *now its possible - pip install mnn opencl not building on pi4 - github.com/doe300/VC4CL (only pi 3 - qengineering.eu/install-opencl-on-raspberry-pi-3.html)
RMBG 2.0 - background remove model - test on raspberry pi 4b
Просмотров 13Месяц назад
huggingface.co/briaai/RMBG-2.0
ruadapt_qwen2.5_3B test on raspberry pi 4b 8gb raspbian bullseye
Просмотров 103Месяц назад
./build/bin/llama-cli -m models/Q4_K_M.gguf -co -cnv -p "You are Qwen, created by Alibaba Cloud. You are a helpful assistant." -fa -ngl 80 -n 512 -t 0.1 выводы: - в большинстве случаев модель выдает правильные развернутые ответы. - иногда допускает грубейшие фактические ошибки - например, о том, что СССР воевал в начале Второй мировой войны на стороне Германии, а потом против. - скорость генера...
ruadapt_qwen2.5_3B test on luckfox 3566 ubuntu 24.04
Просмотров 102Месяц назад
- luckfox 3566 4GB RAM 32Gb emmc - wiki.luckfox.com/Core3566/ - ubuntu 20.04 was updated to 24.04 - llama.cpp built - github.com/ggerganov/llama.cpp/blob/8f275a7c4593aa34147595a90282cf950a853690/docs/build.md#l4 - model rus-rus quantized - huggingface.co/RefalMachine/ruadapt_qwen2.5_3B_ext_u48_instruct_v4_gguf/tree/main ./build/bin/llama-cli -m models/Q4_K_M.gguf -co -cnv -p "You are Qwen, crea...
Mini-Omni2 test on cpu i5-10400 (no cuda)
Просмотров 1062 месяца назад
model speech(or/and image)-to-text. -вопрос можно задать на русском в том числе, ответ всегда на английской. -речь на выходе real-time заикается, разработчики пишут, что это связано с моделью, которая в float32. - готовый аудиофайл в wav без заиканий. github.com/gpt-omni/mini-omni2
yolon11.pt vs yolon11.onnx (imgsz=dynamic) vs yolon11 (imgsz=256) on raspberry pi 4b
Просмотров 352 месяца назад
1400ms - yolo11n.pt 640x640 726ms - yolo11n.onnx imgsz=dynamic int8 333ms - yolo11n.onnx imgsz=256 int8
stable diffusion mojo vs stable diffusion onnx inference tests
Просмотров 632 месяца назад
stable diffusion mojo vs stable diffusion onnx inference tests
together.ai api test (meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo - image-to-text multi-modal)
Просмотров 552 месяца назад
together.ai api test (meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo - image-to-text multi-modal)
mojo(fast python) on raspberry pi - install and some tests
Просмотров 592 месяца назад
mojo(fast python) on raspberry pi - install and some tests
how to convert craft-text-detector .pt model to .onnx model
Просмотров 252 месяца назад
how to convert craft-text-detector .pt model to .onnx model
craft-text-detector onnx inference on raspberry pi 4b
Просмотров 452 месяца назад
craft-text-detector onnx inference on raspberry pi 4b
whisper vs whisper-cpp vs whisper-jax vs vosk on raspberry pi 4b
Просмотров 853 месяца назад
whisper vs whisper-cpp vs whisper-jax vs vosk on raspberry pi 4b
аудио с таджикского в текст с помощью vosk на raspberry pi4b
Просмотров 683 месяца назад
аудио с таджикского в текст с помощью vosk на raspberry pi4b
HLK-LD2450 test on raspberry pi 4 uart
Просмотров 1503 месяца назад
HLK-LD2450 test on raspberry pi 4 uart
yolov9-t-onnx - test on raspberry pi 4b
Просмотров 673 месяца назад
yolov9-t-onnx - test on raspberry pi 4b
llava-v1.5-7b-4096-preview from groq - test on raspberry pi 4b
Просмотров 1683 месяца назад
llava-v1.5-7b-4096-preview from groq - test on raspberry pi 4b
saiga_llama3_8b_gguf - test models q2 and q4 on raspberry pi 4b
Просмотров 433 месяца назад
saiga_llama3_8b_gguf - test models q2 and q4 on raspberry pi 4b
mini-omni (Real-time speech-to-speech) test on raspberry pi 4b 8Gb RAM - very slow
Просмотров 2183 месяца назад
mini-omni (Real-time speech-to-speech) test on raspberry pi 4b 8Gb RAM - very slow
prometheus+grafana - monitoring windows and linux PCs from raspberry pi 4b
Просмотров 944 месяца назад
prometheus grafana - monitoring windows and linux PCs from raspberry pi 4b
FLUX:SOTA (shnell) test on RTX 3060 12Gb
Просмотров 3644 месяца назад
FLUX:SOTA (shnell) test on RTX 3060 12Gb
whisper_cpp (speech-to-text) test on raspberry 5b
Просмотров 554 месяца назад
whisper_cpp (speech-to-text) test on raspberry 5b
from version 3.1.0 it apparently no longer works
😭😭 is it true?
Does this also work with 3.1?
this removes some bugs and ghosting
tanks a lot.
Not all heroes wear capes. Thankyou Sir. Still working on 3.0.1
dont say it work on 3 its not smart to put all that info here
@@Arnoud-nf6iz It's free, open source software. Stop worrying so much.
Прикольно. А есть портабл версия, чтобы не морочиться с установкой?
нет. но, думаю, не сложно собрать с pyinstaller.
What kind of model was the model before it was in the ONNX format? I am trying to convert the file into a CoreML model with the ONNX 1.3 package, and it said that it was unable to detect the type of model is was originally (Pytorch, Tensorflow, etc.), so it's throwing an error. Also, sorry if the video already answered this question, I only speak English.
Nevermind, I see in the description it says it is a .pt model
Funciona pero solo en el preview al iniciar no crea la imagen
3.0.1 works, do as he says in the comment, thanks!
Thank u awesome-uploader-dude
How can u do it if you have facefusion on pinokio? 3.0.0.
cuando eecutas facefusion en pinokio te sale stop y View File le das en View File y siges los pasos del video
3.0.1 Работает 04,12,24
I have version 3.0.1, I tried to open the file analyzser, but I can't open it. I'm using Pynthon 3.9.6 why?
For some reason the IDE is acting up just open it in another text editor and make the change there or copy the file to the desktop and make the change there with the IDE and copy it back 👍
just open pinokio and click files find it there its a build in editor there
which python did you install to open the data?
boa constrictor in lil slits
I cannot find this place to change it ..
pinokio < files < find it there chnage values
Hey , can you help me please? Because i don't search driver for this lCD display😢
@alexanderjsjd see links to video.
3.0.1 👍
Can you write an explanation for Mac users? How can we change it?
Thanks boss❤
Nice bro Do you recommend that I use Mojo in my raspberry pi 5 ?
test it to find out.
What about in 3.0.1?
I used pinokio, I don't know where to find the content.py file. With pinokio open, I can "see files" but I can't change it. How would I change it? Thanks
where you saved pinokio: pinokio>api>facefusion pinokio>facefusion>facefusion>"content_analyser.py
open pinokio open on left side files. it has a build in editor Change value and easily safe dont need a special program. stop app restart windows
Worked for me
3.0.0 works, thank you
03.11.2024 works with 3.01, thank you for that great tip!!!
not work in my 3.0.1 😭
@@LuizMoraes-fn5ir what problem did you have?
@@ulauoft I also use version 3.0.1 but I still have the blur picture. What did you do to remove it? I changed the value from 0.8 to 1.0, but no result.
Where is the file in 3.0.1?
@EdwinPouwel open pinokio click files. (on the left). u find ther what you need to change in the youtube video.. click save.. close app.. restart computer
3.0.1 still works 😂
Where can I find the setting to change it this vid is confusing
@ I used video for settings
Hi as a mac user how does one even access this file to change the code?
3.0.1 working
What did you do to get it to work? I changed the value to 1.0 but the blurry picture stays. Need some help.
👍
10/31/2024 still works for 3.0.1 After I saved the change, I had to fully close program and then re-open. When I did that, "poof", the blur was gone :-D
Where do I go to change this setting ?
How can u do it if you have facefusion on pinokio?
Тоже такая проблема. Зарядное устройство всё родное но начал часто перезагружаться. Что можно сделать, подскажите пожалуйста
@AzikKhakimovich снять крышку и приклеить радиатор от raspberry pi на то , что греется.
do you have a tool to translate the text? I would like to translate the game into Italian (google translation) у вас есть инструмент для перевода текста? Я хотел бы перевести игру на итальянский язык.
@LeonardoGanzerli habr.com/ru/articles/787708/
27-10-2024 Jala perfecto Probability limit = 1.00
w, thank you
Remember to stop and re run facefusion
hi sir, im wondering how do you remove the sfw filter in roop unleashed?
16/10/2024 still working on FaceFusion 3.0.0. thanks!
are you sure bro?
dont say that its not smart
Здравствуйте есть какой то у вас контакт для связи? Есть проект именно по маппингу. Можете помочь или подсказать?
@КонстантинОнчуков-т4я poisk123 yandex.ru
working in 3.0 thanks
does it work for the new 3.0 version
yes, works like a charm
Not for me …
@@francoismarousez647try to completely delete the whole pinokio folder and reinstall it with the latest cuda. That worked for me. But in my opinion the 2.6 version of the app is better than the latest one. No need to change. I would roll it back, tbh.
@@Turbulent2000 can you let me know what you did? Or can you send me a copy of your content_analyzer file to see if this solves my problem?
@ I’ll share you a copy a bit later, when I’m home
its not working
working on 3.0.0 as of 25/9/2024
Help me on video 🤣
Does anyone know how to bypass on 3.0?
3.0.0 is working, thanks
how it could be on Mac??
@@physobornsicx idk, I’m on the windows
@@UltraMarine_1PSUT12 真羨慕你，感謝回覆，兄弟
Still works on 3.0.0
I changed it but now the faces don't swap... Do you know how to make it work? I'm on 3.0
@@ilanchico8375 check that you followed the instructions carefully and correctly. I found the file, edited in VB Studio to comment out the 0.8 line and add the 1.00 line and it's working for me in 3.0
@@ilanchico8375 it does work, but it's a bit flaky. A better approach is to go down to the actual valuation line and set it to always return false. Search for: return probability > PROBABILITY_LIMIT and change to: return False #probability > PROBABILITY_LIMIT
@@ilanchico8375 You did something wrong, I change it and works fine!
not smart to say that stuff
2.6.1 stil working
Funciona?
плохо, но funciona
Thanks for this video . Can i contact you on telegram please
Hello sir, thank you for this explanation. Can I contact you privately, please?
how u see that ?
Great video! Thank you! What is the inference time you are seeing for a single image?
cant remember exactly but as to video: 3 images with 20sec each.
@@АльбертИванов-ц4х Thanks! Do you think if I quantize it, it will run <1FPS?
make a try. but i doubt it. better take special arducam tof camera for real-time.