Software Engineering Courses (SECourses)•16mo ago

I can't find a solution how to generate a queue of 100 different promts in order. The context window

I can't find a solution how to generate a queue of 100 different promts in order. The context window allows you to enter a lot of text with promts where they are placed in one line, but only the last one is launched

Ttruellusion I can't find a solution how to generate a queue of 100 different promts in order...

druhl•9/8/24, 3:28 PM

What are you using? SwarmUI generator?

druhl•9/8/24, 3:29 PM

Use seperator || to separate the prompts.

Dreamer@TDFilmStudio•9/8/24, 3:30 PM

@Dr. Furkan Gözükara Locking horns with GPT-4V https://huggingface.co/OpenGVLab/InternVL-Chat-V1-5

OpenGVLab/InternVL-Chat-V1-5 · Hugging Face

Ddruhl So, I just terminate the massed compute instance and it all goes away correct? �...

Furkan Gözükara SECourses•9/8/24, 3:41 PM

yes . you can use hugging face for backup which i use

Xxlads It’s not showing up for me

Furkan Gözükara SECourses•9/8/24, 3:41 PM

you need to generate if folder missing

AAIGambino whats the prompt here? lol love it

Furkan Gözükara SECourses•9/8/24, 3:43 PM

shared the prompts here , will put into our zip file as well : https://gist.github.com/FurkanGozukara/12c837939ca3fc59abc04d8bd44876ab

Gist

100 flux prompts.txt

100 flux prompts.txt. GitHub Gist: instantly share code, notes, and snippets.

Pprotector131090 Hello! whats the news on Flux Dreambooth training in Kohya on 24 vram ? possible...

Furkan Gözükara SECourses•9/8/24, 3:43 PM

i think yes and hopefully gonna start tests today

DDreamer@TDFilmStudio I have trained 3 custom Flux loras till now and everytime, I am getting scan lin...

Furkan Gözükara SECourses•9/8/24, 3:44 PM

did you notice that in my grids?

Furkan Gözükara SECourses•9/8/24, 3:44 PM

i saw such thing when only i used 2x upscale of swarmui

MMaxivi @Dr. Furkan Gözükara https://huggingface.co/OpenGVLab/InternVL2-8B/tree/main th...

Furkan Gözükara SECourses•9/8/24, 3:45 PM

do you use system prompt? if so what is it

FFurkan Gözükara SECourses do you use system prompt? if so what is it

Maxivi•9/8/24, 4:10 PM

just caption the image with details, colors, makeup, items, objects, emotions, art style, drawing style and objects but do not add any description or comment. do not miss any item in the given image, very simple sentance.

Maxivi•9/8/24, 4:10 PM

they have a demo interface

Maxivi•9/8/24, 4:10 PM

https://internvl.readthedocs.io/en/latest/get_started/local_chat_demo.html

Maxivi•9/8/24, 4:12 PM

@Dr. Furkan Gözükara its quite nice actually, able to capture details better as well. i've tried longer prompts too works quite nice

Maxivi•9/8/24, 4:12 PM

i think it would be better than joy and cog for style training too

FFurkan Gözükara SECourses you need to generate if folder missing

xlads•9/8/24, 4:13 PM

just create a folder titled Umet in the model files inside of swarmui?

Dreamer@TDFilmStudio•9/8/24, 4:13 PM

@Dr. Furkan Gözükara Yes please see if InternVL2 is possible

Maxivi•9/8/24, 4:13 PM

it crazy that the 8b models outperforms many of the others

Maxivi•9/8/24, 4:13 PM

26b 4bit it possilbe as well, its the best one from my testing

MMaxivi just caption the image with details, colors, makeup, items, objects, emotions, a...

Furkan Gözükara SECourses•9/8/24, 4:14 PM

they lack Gradio Demo

Xxlads just create a folder titled Umet in the model files inside of swarmui?

Furkan Gözükara SECourses•9/8/24, 4:14 PM

unet

Furkan Gözükara SECourses•9/8/24, 4:14 PM

exactly as that

Maxivi•9/8/24, 4:14 PM

they have streamlit demo

Furkan Gözükara SECourses•9/8/24, 4:15 PM

their demo down

Furkan Gözükara SECourses•9/8/24, 4:15 PM

Calling st.rerun() within a callback is a no-op.

Maxivi•9/8/24, 4:16 PM

https://internvl.opengvlab.com/

Maxivi•9/8/24, 4:16 PM

this one? its working for me

Furkan Gözükara SECourses•9/8/24, 4:16 PM

testing here

Furkan Gözükara SECourses•9/8/24, 4:16 PM

https://huggingface.co/spaces/OpenGVLab/InternVL

InternVL - a Hugging Face Space by OpenGVLab

Maxivi•9/8/24, 4:16 PM

both work

Maxivi•9/8/24, 4:16 PM

even for me

Furkan Gözükara SECourses•9/8/24, 4:17 PM

Maxivi•9/8/24, 4:18 PM

Seems pretty good!

Furkan Gözükara SECourses•9/8/24, 4:18 PM

Furkan Gözükara SECourses•9/8/24, 4:18 PM

now i will compare generated images on swarmui

FFurkan Gözükara SECourses Click to see attachment

Maxivi•9/8/24, 4:19 PM

i think in terms of training, when you train this many tokens for a person its not good, but the simplified but accurate ones from internvl gave me quite good results

MMaxivi i think in terms of training, when you train this many tokens for a person its n...

Furkan Gözükara SECourses•9/8/24, 4:19 PM

well i think for training a person no captions better :d

FFurkan Gözükara SECourses well i think for training a person no captions better :d

Maxivi•9/8/24, 4:20 PM

depends, yours are usually overtrained

xlads•9/8/24, 4:26 PM

okay i made the unet file inside of models then restarted/updated but still getting same error saying "All available backends failed to load the model"