it is consistent as long as it is same person
it is consistent as long as it is same person
Fand no other persons exists in dataset
Bwhat about he is having beard and diff hairstyle is that inconsitent , if yes then what to take care in captioning so we are not over eng things in the captioning for the lora traning
B@Dr. Furkan Gözükara
Fi think still not needed
Fmmaudio almost ready
F
TThis is my latest NEGATIVE Promt. It is meant for jus a regular realistic video. Wan tends to shift video styles depending on your prompt, lets say you want aliesn in your video, all of a sudden it starts making 3D render or animation instead of realistc video. This prompt will lock you in realistic style and produce less shitty videos by a good margin than |no negative prompt at all. Dont waste your time. Take it ant tweak to your needs:
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, inaccurate, distorted, motion smear, motion blur, motion stutter, video noise, video artifacts, warped, motionless, 3D render, animation, anime, 3D game, cartoon, comic book, manga, stylized, abstract
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, inaccurate, distorted, motion smear, motion blur, motion stutter, video noise, video artifacts, warped, motionless, 3D render, animation, anime, 3D game, cartoon, comic book, manga, stylized, abstract
Fapp ready publishing
Fwill make a video too
FF
Fv3 published all features done
Fplease test asap and let me know 
FPatreon
Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon
Fi will try to make kaggle notebook too now
Jwow you are fast i just tested version 2 and it works great, haha have to test your newest version now! 
Fyes please
Fi think it is perfect now with all features
Fand shows on cmd
Ji just used the update.bat is it ok or new install?
Fit should work
TTry 4:5 aspect ratio as it is dominant for mobile photos and Instagram.
All you generated examples are closer to 3:2 aspect ratio that are characteristic of professional cameras
All you generated examples are closer to 3:2 aspect ratio that are characteristic of professional cameras
Tflux dev is very sensetive to aspect ratio
TFor example when trying to generate "video frame" with aspect ratio you can control modern cinema / old movie / Tv soap opera / VHS era feel and so on
A@Dr. Furkan Gözükara do we have tutorial / installer for this ?
https://github.com/ali-vilab/ACE_plus
https://github.com/ali-vilab/ACE_plus
GitHub
Contribute to ali-vilab/ACE_plus development by creating an account on GitHub.
AHas anyone tried it ? if so , let me know please
Awhat token and class did you use?
Fnot yet but definitely i need to make
Fmmaudio working on kaggle
Freally fast
Mhi, Is there any way in Swarm or ComfyUI to remove that overly plastic-looking texture in generations, especially in portraits?
Meverything looks excesively smooth, loosing reality, I need more photographic style
Dthats just Flux
Fusing custom trained checkpoint or lora
Fis solution
Fwhen we train our fine tuned models it also remove that
Ftrue
MI'm using one
MBut it's true that maybe It's not the perfect dataset
MYep I see ... Any other model recomendations to get realistic portraits?
Tyou can't get better results than flux, you just need more effort with it. Consider better prompt engineering
AGitHub
Contribute to ali-vilab/ACE_plus development by creating an account on GitHub.
Tnope
Aany tips on better prompt engineering? is there like a custom gpt out there for flux prompting ?
Tnope, just experiment. There is no single solution that fits all cases
TAlso img2img is a powerful tool, even if you can't get result just with prompt you can use reference images and/or inpainting
Dtheres a myriad of options available. filmic looking loras, checkpoints trained for analog look, you don't need to limit yourself for base flux
FF