I tried lora but I like the outputs that im getting from finetuning. I see fewer overfits and more c
I tried lora but I like the outputs that im getting from finetuning. I see fewer overfits and more consistency in finetuned model.
Fye fine tune best
EI'm sonfused and have to ask again,
am I wrong in that you still can't train a full checkpoint below 80 gb vram? And finetuning means full checkpoint right?
am I wrong in that you still can't train a full checkpoint below 80 gb vram? And finetuning means full checkpoint right?
EThe lora turned out really bad. No shape from prodct at all, it only makes like a genral bag like it dosn't under geometry, or the shape is to complex
Ffull checkpoint can be trained as low as 6 gb vram
F6GB_GPU_5400MB_14.1_second_it_Tier_3_512px.json
Fthis is same as 48 gb config quality
F8GB_GPU_7500MB_20.5_second_it_Tier_1.json
ECould i use the 24 gb config for my rtx 4090?
F100%
Fpay attention to your empty vram
Fit uses 23 gb
Fyou can increase block swap count if you cant have 23 gb free due to other apps
EOk, could I do say 6 different colors of the same bag (same shape) in one checkpoint? I guess I would need captioning then.
Fi think you can train different colors of same bag
UHello,
I'm trying to run grid generator but I get this error, do you know why?
I'm familiar with comfyui but this is my first time trying swarmui
I'm trying to run grid generator but I get this error, do you know why?
I'm familiar with comfyui but this is my first time trying swarmui
U
Fhard to know without seeing all
Fyou can post debug logs here
UI was able to get it working. I pulled the latest code and it started working.
Uwhile generating images in a grid with multiple models, how does inpainting work? which image does it take as reference?
Fwhat kind of inpainting?
Fsegment?
Uyes, to make the face look more like the original character and to make it more clear
Fit inpaints every image
Fit generates
Fit is part of prompt
Uyes that I understand. While generating one image with one model it takes the first image that we generated as reference and inpaints the face right? but in grid generation, I didnt have a first image and I directly started generating images. My doubt is what reference would it take for inpainting if we dont have our first image generated?
Fit takes every generated image
Fand then inpaint face
UOh okay. I thought "1" in 1, 0.7, 0.5 meant take the first image as reference for inpainting the face <segment:yolo-face_yolov9c.pt-1,0.7,0.5//cid=11> that is why I was confused and wanted to know what would happen for the first image generation if we didn't have our first image generated.
F1 means first face in image
Uoh 
I completely misunderstood. Thanks for the clarification.
I completely misunderstood. Thanks for the clarification.Ucan we use ipadapter to use a reference image/face so the generated images are consistent?
similar to segment, do we have anything for ipadapter like this - <ipadapter:test_image.jpg:0.5> ?
similar to segment, do we have anything for ipadapter like this - <ipadapter:test_image.jpg:0.5> ?
Fwe have this but there could be other ways too
FPatreon
Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon
UThank you 
I will take a look!
I will take a look!UI noticed you are using adafactor, what is your take on prodigy? the learning rate will adapt accordingly right? it might consume more vram but what do you think the result quality would be with prodigy?
I might be wrong but because the learning rate adapts, I think we might eliminate the risk of overfitting. Your advise would be helpful.
I might be wrong but because the learning rate adapts, I think we might eliminate the risk of overfitting. Your advise would be helpful.
Fi tested them and none of the others yielded as realistic as adafactor
Fi did a big test recently
UThank you for 15 image dataset, were you able to figure what the unet learning rate was ideal?
for 15 image dataset, were you able to figure what the unet learning rate was ideal?Fyes our rate is ideal
Fjust do at least 200 epoch
Fbut you can do up to like 3000 and compare
Uare you able to share the results for learning purposes?
Ualso for batch size, what number do you recommend? I'm renting A100 gpu. I'm testing with a batch size of 1 for 15 images. I want to increase it but I'm afraid the model might overfit. I can test them myself but I'm paying by the hour so testing all of them is going to burn me out 
Fi recommend bs 1
Fi planned the test but later didnt have time 
UThank you very much. Your testing evaluation is saving my time
Uone more question
you used constant LR scheduler, why not cosine or cosine with restarts?
With the constant scheduler, the model doesn't learn. The training loss doesn't decrease. Is this okay?
you used constant LR scheduler, why not cosine or cosine with restarts?
With the constant scheduler, the model doesn't learn. The training loss doesn't decrease. Is this okay?
Ftraining loss useless