then add 8 for emotions, or maybe sprinkle some emotions across the dataset.
then add 8 for emotions, or maybe sprinkle some emotions across the dataset.
Mas if it's that easy!
Fshouldnt have any diff
Ayou can train a stage 1 model and generate pictures of your subject with emotions
Athen train with a new dataset
Aor use inpainting on flux but haven't tested that method
MI am testing Pulid to do so, without having to do multiple stages, it's pretty good
Amake sure no noise is being generated/blur
MIs this considered noisy? (I am still trying to get rid of the plastic skin)
Mthis is a low res, here's the detail:
Fit looks like cgi though
MAgree, still working on that.
FSDXL training now goes to as low as 10200 MB on Kohya
A@Furkan Gözükara SECourses what's the other unique token for sd called other than ohwx ?
Ahere's another shot I made
A
RHiya - just wondering if anyone knows why SwarmUI inside latest massive compute instance would have trouble finding Flux model? I can see some funky alias stuff happeing towards download folder. I am a comfy user and can point to flux using that the normal way
RI got it working - some funky directory pointing going on in SwarmUI - also i am new to it coming from Comfy background and learing how the Dr does it. Cheers
Jthis new Hunyuan3D 2.0 looks really interesting!
�@Dr. Furkan Gözükara Will you be testing training on Hunyuan video? I am waiting for that.
Yrandom thought, can you make flux loras a gguf???
JWhen i for example extract a lora from Checkpoint XY can i also use it with Checkpoint YX or will i have quality loss? (Both based on Flux) ?
JThink i never saw any lora in gguf format, why would you need that?
WGitHub
GGUF Quantization support for native ComfyUI models - city96/ComfyUI-GGUF
Yloras are gb for flux on 128 rank+ higher unlike sd 3.5/xls
Jlol, just checked, ive trained full checkpoint on a FP16 Model (11 GB , which resulted in finetuned checkpoint with around 22GB, so will the Lora be 11 GB big? why is it that huge?#
VDoc would be buying the Rtx 5090?
VAnd doc what do you think about NVIDIA Project DIGITS? ..Nvidia priced it at 3000$ ...Rtx 5090 is priced at 2000$...
..
..
DWhat is the state-of-the-art of creative upscaling? still SUPIR?
JThats still what im using
JAlso tried some comfy workflows but they cant reach supir level
Dlet's see. I believe DIGITS at 3k for this spec when I have it on my desk. Most likely with NVIDIA, 3k is the price for a DIGITS-060, and the DIGITS-090 is 3x that
Dthanks
DSUPIR was using JuggernautXL when I last used it. Have they upgraded to newer models such as Flux?
J@Furkan Gözükara SECourses Is Pinokio used for anything at massedcompute or can i delete it for more space?
JIm still using XL Models for Upscaling, dont even know if Flux works with supir
Ddon't know either, but I had problems with SUPIR with teeth and other things XL typically has problems with, or needs ADetailer to fix it. So using the newer models would make sense
JNever had those problems with realvis
JHow can i view the metadata of a flux checkpoint?
Dwhat do you mean, what metadata
Jlike info tab in a1111 when selecting a checkpoint
Ddid you just answer your own question? 
JNo does not work with flux checkpoints
Pthere are rumors about a new nvidia workstation grade card, with 96gb vram, price will be like 10k$ or even more and im pretty sure it will destroy the project digits in performance
i have a feeling that digits will be a big disappointment, but still im hyped about the release 
i have a feeling that digits will be a big disappointment, but still im hyped about the release 
Dwhat do you mean rumors? that's similar to their current lineup. of course they will release blackwell workstation cards
Prumors, until they are confirmed
Dthe promise of DIGITS was to have 128 GB mixed RAM/vRAM for a reasonable price, which they could actually do because it's hard to abuse a desktop PC in datacenters. that's probably the main reason why most cards only have 16 GB vram, to avoid AI companies to buy consumer cards
Dit's not a rumor if it already exists.
Pwhere