tradfusion-v2-training-files / configs /2023-10-22T14-53-45-project.yaml
hdparmar's picture
Upload folder using huggingface_hub
e2b4f23
raw
history blame
No virus
2.49 kB
model:
base_learning_rate: 0.0001
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
linear_start: 0.00085
linear_end: 0.012
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: image
cond_stage_key: txt
image_size: 64
channels: 4
cond_stage_trainable: false
conditioning_key: crossattn
scale_factor: 0.18215
scheduler_config:
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps:
- 10000
cycle_lengths:
- 10000000000000
f_start:
- 1.0e-06
f_max:
- 1.0
f_min:
- 1.0
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
image_size: 32
in_channels: 4
out_channels: 4
model_channels: 320
attention_resolutions:
- 4
- 2
- 1
num_res_blocks: 2
channel_mult:
- 1
- 2
- 4
- 4
num_heads: 8
use_spatial_transformer: true
transformer_depth: 1
context_dim: 768
use_checkpoint: true
legacy: false
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
ckpt_path: models/first_stage_models/kl-f8/model.ckpt
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
data:
target: main.DataModuleFromConfig
params:
batch_size: 4
num_workers: 4
num_val_workers: 0
train:
target: ldm.data.simple.hf_dataset
params:
name: hdparmar/irish-traditional-tunes
image_transforms:
- target: torchvision.transforms.RandomHorizontalFlip
validation:
target: ldm.data.simple.TextOnly
params:
captions:
- An Irish Traditional tune with vibrant bouzouki strums
- An Irish Traditional Tune
- A traditional Irish slip jig rhythm
- A lively Irish Traditional Tune with a prominent fiddle lead
output_size: 512
n_gpus: 2