Comments (8)
from kohya_ss.
bucket_no_upscale = true
bucket_reso_steps = 64
cache_latents = true
cache_latents_to_disk = true
caption_dropout_every_n_epochs = 0
caption_dropout_rate = 0
caption_extension = ".txt"
clip_skip = 1
dynamo_backend = "no"
enable_bucket = true
epoch = 100
gradient_accumulation_steps = 1
gradient_checkpointing = true
huber_c = 0.1
huber_schedule = "snr"
keep_tokens = 1
learning_rate = 0.0001
logging_dir = " /data/train/ssyy/log"
loss_type = "l2"
lr_scheduler = "constant"
lr_scheduler_args = []
lr_scheduler_num_cycles = 1
lr_scheduler_power = 1
lr_warmup_steps = 0
max_bucket_reso = 2048
max_data_loader_n_workers = 0
max_grad_norm = 1
max_timestep = 900
max_token_length = 75
max_train_steps = 3975
min_bucket_reso = 256
min_snr_gamma = 5
min_timestep = 100
mixed_precision = "fp16"
multires_noise_discount = 0
network_alpha = 64
network_args = []
network_dim = 128
network_dropout = 0
network_module = "networks.lora"
no_half_vae = true
noise_offset_type = "Original"
optimizer_type = "AdamW"
optimizer_args = []
output_dir = " /data/train/ssyy/model"
output_name = "LoRA-ssyy-sdxl-v2"
pretrained_model_name_or_path = "stabilityai/stable-diffusion-xl-base-1.0"
prior_loss_weight = 1
resolution = "1024,1024"
sample_every_n_epochs = 5
sample_prompts = " /data/train/ssyy/model/prompt.txt"
sample_sampler = "euler"
save_every_n_epochs = 10
save_model_as = "safetensors"
save_precision = "fp16"
scale_weight_norms = 0
seed = 12345
text_encoder_lr = 0.0001
train_batch_size = 4
train_data_dir = " /data/train/ssyy/img"
training_comment = "trigger: yeonhwa"
unet_lr = 0.0001
xformers = true
from kohya_ss.
from kohya_ss.
from kohya_ss.
When I reinstalled the entire project, new problems appeared
from kohya_ss.
The problem was solved. I reinstalled the project and then performed the operations in "prepare training data". The program recognized all the paths and started working.
from kohya_ss.
I only have 25 pictures, but the program determines that I have 50 pictures
from kohya_ss.
Awesome!
from kohya_ss.
Related Issues (20)
- MultipleInvalid: extra keys not allowed @ data['datasets'][0]['subsets'][1]['is_reg']
- Could anyone help me qq?
- dreambooth lora extraction = bad results.
- Full FP16 Dreambooth for SDXL does not work HOT 2
- Missing keys & size mismatch when merging LORAs
- Blue screen "video scheduler internal error" when using SD 3 branch with SD 3 training (normal branch XL works fine) HOT 1
- SD3 Gui Sampling + lora extraction HOT 1
- Request to add controlnet fine-tuning
- Network dropout and samples
- RuntimeError: The size of tensor a (8) must match the size of tensor b (2744) at non-singleton dimension 1
- ValueError: num_samples should be a positive integer value, but got num_samples=0 HOT 1
- Security vulnerabilties: gradio and onnx HOT 2
- request to add weighted captions for SDXL HOT 2
- Runpod does not work.
- WD14 captioning in Runpod not working
- No module named 'xformers' on AMD rx7800XT [fedora40]
- AssertionError Related to Bucket Info in Fine-Tuning Script
- Training [LoRA] has ended, returned non-zero exit status 1 HOT 2
- ChainedScheduler and SequentialLR?
- SD3 into main branch
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from kohya_ss.