Upload folder using huggingface_hub
Browse files- checkpoint-12400/optimizer.bin +3 -0
- checkpoint-12400/optimizer_1.bin +3 -0
- checkpoint-12400/random_states_0.pkl +3 -0
- checkpoint-12400/scaler.pt +3 -0
- checkpoint-12400/scheduler.bin +3 -0
- checkpoint-12400/unet/config.json +73 -0
- checkpoint-12400/unet/diffusion_pytorch_model.safetensors +3 -0
- logs/text2image-fine-tune/1755258183.3891134/events.out.tfevents.1755258183.a9839099f4b1.4401.1 +3 -0
- logs/text2image-fine-tune/1755258183.3985848/hparams.yml +55 -0
- logs/text2image-fine-tune/events.out.tfevents.1755258183.a9839099f4b1.4401.0 +3 -0
checkpoint-12400/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22bc4974059ac0e5be3ad5b3c47366f85f0cd1d79e8f66520481f895c9e37fce
|
| 3 |
+
size 1496291698
|
checkpoint-12400/optimizer_1.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b9ed2e725994ae615c69b801d4e79f2132a1efdb435e6d3b1582c252329bbc8
|
| 3 |
+
size 15431330
|
checkpoint-12400/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f70a33c4434ce98815e772b00e6308090f67d01bc62c13da867c8be96d03682e
|
| 3 |
+
size 14344
|
checkpoint-12400/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9e0002b451a3973b31f81369995225134c80bddcce906db92b3a5878af143e1
|
| 3 |
+
size 988
|
checkpoint-12400/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13501d4a498f9bee6eb7dc634c98c0f8822a253871435585a7bda7e613d8a7a0
|
| 3 |
+
size 1000
|
checkpoint-12400/unet/config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.26.3",
|
| 4 |
+
"_name_or_path": "k5pcmlra2-test",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": "text_time",
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": 256,
|
| 9 |
+
"attention_head_dim": [
|
| 10 |
+
5,
|
| 11 |
+
10,
|
| 12 |
+
20
|
| 13 |
+
],
|
| 14 |
+
"attention_type": "default",
|
| 15 |
+
"block_out_channels": [
|
| 16 |
+
320,
|
| 17 |
+
640,
|
| 18 |
+
1280
|
| 19 |
+
],
|
| 20 |
+
"center_input_sample": false,
|
| 21 |
+
"class_embed_type": null,
|
| 22 |
+
"class_embeddings_concat": false,
|
| 23 |
+
"conv_in_kernel": 3,
|
| 24 |
+
"conv_out_kernel": 3,
|
| 25 |
+
"cross_attention_dim": 2048,
|
| 26 |
+
"cross_attention_norm": null,
|
| 27 |
+
"down_block_types": [
|
| 28 |
+
"DownBlock2D",
|
| 29 |
+
"CrossAttnDownBlock2D",
|
| 30 |
+
"CrossAttnDownBlock2D"
|
| 31 |
+
],
|
| 32 |
+
"downsample_padding": 1,
|
| 33 |
+
"dropout": 0.0,
|
| 34 |
+
"dual_cross_attention": false,
|
| 35 |
+
"encoder_hid_dim": null,
|
| 36 |
+
"encoder_hid_dim_type": null,
|
| 37 |
+
"flip_sin_to_cos": true,
|
| 38 |
+
"freq_shift": 0,
|
| 39 |
+
"in_channels": 4,
|
| 40 |
+
"layers_per_block": 2,
|
| 41 |
+
"mid_block_only_cross_attention": null,
|
| 42 |
+
"mid_block_scale_factor": 1,
|
| 43 |
+
"mid_block_type": "UNetMidBlock2D",
|
| 44 |
+
"norm_eps": 1e-05,
|
| 45 |
+
"norm_num_groups": 32,
|
| 46 |
+
"num_attention_heads": null,
|
| 47 |
+
"num_class_embeds": null,
|
| 48 |
+
"only_cross_attention": false,
|
| 49 |
+
"out_channels": 4,
|
| 50 |
+
"projection_class_embeddings_input_dim": 2816,
|
| 51 |
+
"resnet_out_scale_factor": 1.0,
|
| 52 |
+
"resnet_skip_time_act": false,
|
| 53 |
+
"resnet_time_scale_shift": "default",
|
| 54 |
+
"reverse_transformer_layers_per_block": null,
|
| 55 |
+
"sample_size": 128,
|
| 56 |
+
"time_cond_proj_dim": null,
|
| 57 |
+
"time_embedding_act_fn": null,
|
| 58 |
+
"time_embedding_dim": null,
|
| 59 |
+
"time_embedding_type": "positional",
|
| 60 |
+
"timestep_post_act": null,
|
| 61 |
+
"transformer_layers_per_block": [
|
| 62 |
+
1,
|
| 63 |
+
1,
|
| 64 |
+
2
|
| 65 |
+
],
|
| 66 |
+
"up_block_types": [
|
| 67 |
+
"CrossAttnUpBlock2D",
|
| 68 |
+
"CrossAttnUpBlock2D",
|
| 69 |
+
"UpBlock2D"
|
| 70 |
+
],
|
| 71 |
+
"upcast_attention": null,
|
| 72 |
+
"use_linear_projection": true
|
| 73 |
+
}
|
checkpoint-12400/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:751ed2b7b8fcfa8c864f0d3cfa49cf70364ddf000bd4064ff22cfa68b78b1989
|
| 3 |
+
size 2980972328
|
logs/text2image-fine-tune/1755258183.3891134/events.out.tfevents.1755258183.a9839099f4b1.4401.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76878e9643e29d089ec99a62bc7d3e85ab61b81fffde9f89f7c18d3ac2aadf07
|
| 3 |
+
size 2841
|
logs/text2image-fine-tune/1755258183.3985848/hparams.yml
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.0
|
| 5 |
+
adv_lr: 1.0e-05
|
| 6 |
+
adv_weight: 0.1
|
| 7 |
+
allow_tf32: true
|
| 8 |
+
cache_dir: null
|
| 9 |
+
cast_teacher_unet: false
|
| 10 |
+
center_crop: false
|
| 11 |
+
checkpointing_steps: 200
|
| 12 |
+
checkpoints_total_limit: 10
|
| 13 |
+
dataloader_num_workers: 1
|
| 14 |
+
enable_xformers_memory_efficient_attention: true
|
| 15 |
+
gradient_accumulation_steps: 10
|
| 16 |
+
gradient_checkpointing: true
|
| 17 |
+
hub_model_id: null
|
| 18 |
+
hub_token: null
|
| 19 |
+
huber_c: 0.001
|
| 20 |
+
learning_rate: 2.0e-06
|
| 21 |
+
local_rank: -1
|
| 22 |
+
logging_dir: logs
|
| 23 |
+
lora_rank: 64
|
| 24 |
+
loss_type: huber
|
| 25 |
+
lr_scheduler: constant
|
| 26 |
+
lr_warmup_steps: 500
|
| 27 |
+
max_grad_norm: 1.0
|
| 28 |
+
max_train_samples: 4000000
|
| 29 |
+
max_train_steps: 12400
|
| 30 |
+
mixed_precision: fp16
|
| 31 |
+
multiphase: 1
|
| 32 |
+
not_apply_cfg_solver: false
|
| 33 |
+
num_ddim_timesteps: 40
|
| 34 |
+
num_train_epochs: 62
|
| 35 |
+
output_dir: k5pcmlra2-test
|
| 36 |
+
pretrained_teacher_model: segmind/Segmind-Vega
|
| 37 |
+
pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
|
| 38 |
+
proportion_empty_prompts: 0
|
| 39 |
+
push_to_hub: false
|
| 40 |
+
random_flip: false
|
| 41 |
+
report_to: tensorboard
|
| 42 |
+
resolution: 512
|
| 43 |
+
resume_from_checkpoint: checkpoint-12200
|
| 44 |
+
revision: null
|
| 45 |
+
scale_lr: false
|
| 46 |
+
seed: null
|
| 47 |
+
teacher_revision: null
|
| 48 |
+
tracker_project_name: text2image-fine-tune
|
| 49 |
+
train_batch_size: 4
|
| 50 |
+
train_shards_path_or_url: null
|
| 51 |
+
use_8bit_adam: true
|
| 52 |
+
use_fix_crop_and_size: false
|
| 53 |
+
validation_steps: 500000
|
| 54 |
+
w_max: 7.0
|
| 55 |
+
w_min: 6.0
|
logs/text2image-fine-tune/events.out.tfevents.1755258183.a9839099f4b1.4401.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0fa3e21b50ebf0c08b69b564e37bdb25893498e225314218e8f9cd82b3a0dcc
|
| 3 |
+
size 21888
|