End of training
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .ipynb_checkpoints/image_0-checkpoint.png +0 -0
- .ipynb_checkpoints/image_1-checkpoint.png +0 -0
- .ipynb_checkpoints/image_2-checkpoint.png +0 -0
- .ipynb_checkpoints/image_3-checkpoint.png +0 -0
- README.md +50 -0
- checkpoint-0/model.safetensors +3 -0
- checkpoint-0/optimizer.bin +3 -0
- checkpoint-0/random_states_0.pkl +3 -0
- checkpoint-0/scaler.pt +3 -0
- checkpoint-0/scheduler.bin +3 -0
- checkpoint-10/optimizer.bin +3 -0
- checkpoint-10/random_states_0.pkl +3 -0
- checkpoint-10/scaler.pt +3 -0
- checkpoint-10/scheduler.bin +3 -0
- checkpoint-10/unet/config.json +73 -0
- checkpoint-10/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
- checkpoint-10/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
- checkpoint-10/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
- checkpoint-1000/model.safetensors +3 -0
- checkpoint-1000/optimizer.bin +3 -0
- checkpoint-1000/random_states_0.pkl +3 -0
- checkpoint-1000/scaler.pt +3 -0
- checkpoint-1000/scheduler.bin +3 -0
- checkpoint-1000/unet/config.json +73 -0
- checkpoint-1000/unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
- checkpoint-1000/unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
- checkpoint-1000/unet/diffusion_pytorch_model.safetensors.index.json +0 -0
- image_0.png +0 -0
- image_1.png +0 -0
- image_2.png +0 -0
- image_3.png +0 -0
- logs/text2image-fine-tune-sdxl/1731332400.8098605/events.out.tfevents.1731332400.scene-gen-ai-v4-0.540.1 +3 -0
- logs/text2image-fine-tune-sdxl/1731332400.8112276/hparams.yml +58 -0
- logs/text2image-fine-tune-sdxl/1731336010.2398946/events.out.tfevents.1731336010.scene-gen-ai-v4-0.812.1 +3 -0
- logs/text2image-fine-tune-sdxl/1731336010.2415638/hparams.yml +58 -0
- logs/text2image-fine-tune-sdxl/1731338666.0457904/events.out.tfevents.1731338666.scene-gen-ai-v4-0.1276.1 +3 -0
- logs/text2image-fine-tune-sdxl/1731338666.047378/hparams.yml +58 -0
- logs/text2image-fine-tune-sdxl/1731339823.9533772/events.out.tfevents.1731339823.scene-gen-ai-v4-0.1463.1 +3 -0
- logs/text2image-fine-tune-sdxl/1731339823.9552855/hparams.yml +58 -0
- logs/text2image-fine-tune-sdxl/1731346828.0336745/events.out.tfevents.1731346828.scene-gen-ai-v4-0.2415.1 +3 -0
- logs/text2image-fine-tune-sdxl/1731346828.035174/hparams.yml +58 -0
- logs/text2image-fine-tune-sdxl/1731352544.2337453/events.out.tfevents.1731352544.scene-gen-ai-v4-0.2709.1 +3 -0
- logs/text2image-fine-tune-sdxl/1731352544.2352123/hparams.yml +58 -0
- logs/text2image-fine-tune-sdxl/1731361202.666019/events.out.tfevents.1731361202.scene-gen-ai-v4-0.3445.1 +3 -0
- logs/text2image-fine-tune-sdxl/1731361202.6674397/hparams.yml +58 -0
- logs/text2image-fine-tune-sdxl/1731412552.530759/events.out.tfevents.1731412552.scene-gen-ai-v4-0.4068.1 +3 -0
- logs/text2image-fine-tune-sdxl/1731412552.5325375/hparams.yml +58 -0
- logs/text2image-fine-tune-sdxl/events.out.tfevents.1731332400.scene-gen-ai-v4-0.540.0 +3 -0
- logs/text2image-fine-tune-sdxl/events.out.tfevents.1731336010.scene-gen-ai-v4-0.812.0 +3 -0
- logs/text2image-fine-tune-sdxl/events.out.tfevents.1731338665.scene-gen-ai-v4-0.1276.0 +3 -0
.ipynb_checkpoints/image_0-checkpoint.png
ADDED
|
.ipynb_checkpoints/image_1-checkpoint.png
ADDED
|
.ipynb_checkpoints/image_2-checkpoint.png
ADDED
|
.ipynb_checkpoints/image_3-checkpoint.png
ADDED
|
README.md
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: stabilityai/stable-diffusion-xl-base-1.0
|
| 3 |
+
library_name: diffusers
|
| 4 |
+
license: creativeml-openrail-m
|
| 5 |
+
tags:
|
| 6 |
+
- stable-diffusion-xl
|
| 7 |
+
- stable-diffusion-xl-diffusers
|
| 8 |
+
- text-to-image
|
| 9 |
+
- diffusers-training
|
| 10 |
+
- diffusers
|
| 11 |
+
- stable-diffusion-xl
|
| 12 |
+
- stable-diffusion-xl-diffusers
|
| 13 |
+
- text-to-image
|
| 14 |
+
- diffusers-training
|
| 15 |
+
- diffusers
|
| 16 |
+
inference: true
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
<!-- This model card has been generated automatically according to the information the training script had access to. You
|
| 20 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
# Text-to-image finetuning - Brvcket/test
|
| 24 |
+
|
| 25 |
+
This pipeline was finetuned from **stabilityai/stable-diffusion-xl-base-1.0** on the **lambdalabs/naruto-blip-captions** dataset. Below are some example images generated with the finetuned pipeline using the following prompt: a cute Sundar Pichai creature:
|
| 26 |
+
|
| 27 |
+

|
| 28 |
+

|
| 29 |
+

|
| 30 |
+

|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
Special VAE used for training: None.
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
## Intended uses & limitations
|
| 37 |
+
|
| 38 |
+
#### How to use
|
| 39 |
+
|
| 40 |
+
```python
|
| 41 |
+
# TODO: add an example code snippet for running this diffusion pipeline
|
| 42 |
+
```
|
| 43 |
+
|
| 44 |
+
#### Limitations and bias
|
| 45 |
+
|
| 46 |
+
[TODO: provide examples of latent issues and potential remediations]
|
| 47 |
+
|
| 48 |
+
## Training details
|
| 49 |
+
|
| 50 |
+
[TODO: describe the data used to train the model]
|
checkpoint-0/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40582c2d826aff7528a3b25e76530d6cdb519d40573d149385db652bb6794a95
|
| 3 |
+
size 10270077736
|
checkpoint-0/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:146470be27b80427b65c56a9d5e6bbc1cef34cccf41a14819d08676538ea50f5
|
| 3 |
+
size 20541173449
|
checkpoint-0/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1c05411d9c2fcf51cafe8572e9df7d54eb2a629850a2f3414a0212c3c800076
|
| 3 |
+
size 14727
|
checkpoint-0/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:909ffc5e40adcfcc03f8fb8e8cc5a6605d5aaa37643bab9d485939a891938ae9
|
| 3 |
+
size 557
|
checkpoint-0/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e44312a25357272b087dbcd9aabcb32e966ed8c4b8f09900e4a4c149043c248
|
| 3 |
+
size 563
|
checkpoint-10/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a901b5540e1bf09fee7fbf9e18d663f709f6ee7bee0ec6b5984bac7f45fb339
|
| 3 |
+
size 20541173449
|
checkpoint-10/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f412f47ce76edb6f9f01d64dac30929f3878117870346f7295032bc9ec63c41
|
| 3 |
+
size 14663
|
checkpoint-10/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:285e76ebe66a23f043b42182e14294a93d529fdc5c0c08159fd9fc10bbeaad36
|
| 3 |
+
size 557
|
checkpoint-10/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:715829e32fb165fa1a4f8e58725497d96735edca5fca51b555511ac1bfc4ed5a
|
| 3 |
+
size 563
|
checkpoint-10/unet/config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.31.0.dev0",
|
| 4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
| 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": "UNetMidBlock2DCrossAttn",
|
| 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 |
+
2,
|
| 64 |
+
10
|
| 65 |
+
],
|
| 66 |
+
"up_block_types": [
|
| 67 |
+
"CrossAttnUpBlock2D",
|
| 68 |
+
"CrossAttnUpBlock2D",
|
| 69 |
+
"UpBlock2D"
|
| 70 |
+
],
|
| 71 |
+
"upcast_attention": null,
|
| 72 |
+
"use_linear_projection": true
|
| 73 |
+
}
|
checkpoint-10/unet/diffusion_pytorch_model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c03d560e86d1e18fccc5e16f5d446c215077beacfc1803ef0a0a0f31ecbb582e
|
| 3 |
+
size 9988139160
|
checkpoint-10/unet/diffusion_pytorch_model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dad645735ccde3f94efd1c9f456c9b75c0bafbd796329c230ccba1ad91abed43
|
| 3 |
+
size 281938304
|
checkpoint-10/unet/diffusion_pytorch_model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c35c6bf0a0f36b2dac76d366f54ae0fe9e0d22b02fd3a7a1ffd8255931930f6
|
| 3 |
+
size 10270077736
|
checkpoint-1000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f66f6beb23eb8d0f79ac1717b198286815a220dd75b438d826ac3ceb1c5e7f55
|
| 3 |
+
size 20541173449
|
checkpoint-1000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:201a0dc48092a545be0a353419d4c770d95e0786400c376aebe37112e11fe636
|
| 3 |
+
size 14663
|
checkpoint-1000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ef4512ee578f7df5b13e2e3b75baf09a7fafaaea150f2fa331e91ea839fc265
|
| 3 |
+
size 557
|
checkpoint-1000/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4db4cf2e94898fdabcf298901aa7b9ecf06ae3b38183fd7ba2cb2e9c7ce68e56
|
| 3 |
+
size 563
|
checkpoint-1000/unet/config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.31.0.dev0",
|
| 4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
| 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": "UNetMidBlock2DCrossAttn",
|
| 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 |
+
2,
|
| 64 |
+
10
|
| 65 |
+
],
|
| 66 |
+
"up_block_types": [
|
| 67 |
+
"CrossAttnUpBlock2D",
|
| 68 |
+
"CrossAttnUpBlock2D",
|
| 69 |
+
"UpBlock2D"
|
| 70 |
+
],
|
| 71 |
+
"upcast_attention": null,
|
| 72 |
+
"use_linear_projection": true
|
| 73 |
+
}
|
checkpoint-1000/unet/diffusion_pytorch_model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:882b6b49e6f7086ac60eb2518159f0f32bc771767ac2f95e8f2086dd1c0e27c7
|
| 3 |
+
size 9988139160
|
checkpoint-1000/unet/diffusion_pytorch_model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3282cffdf120993d63fe2a1e52bbfd1330d13cde2d5dbad804c11da4d62f57b3
|
| 3 |
+
size 281938304
|
checkpoint-1000/unet/diffusion_pytorch_model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
image_0.png
ADDED
|
image_1.png
ADDED
|
image_2.png
ADDED
|
image_3.png
ADDED
|
logs/text2image-fine-tune-sdxl/1731332400.8098605/events.out.tfevents.1731332400.scene-gen-ai-v4-0.540.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40cd701d86922e4bc38266e3090afc6774fdf94e8086b6428a43b118cf8c3231
|
| 3 |
+
size 2642
|
logs/text2image-fine-tune-sdxl/1731332400.8112276/hparams.yml
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.01
|
| 5 |
+
allow_tf32: false
|
| 6 |
+
cache_dir: null
|
| 7 |
+
caption_column: text
|
| 8 |
+
center_crop: false
|
| 9 |
+
checkpointing_steps: 10
|
| 10 |
+
checkpoints_total_limit: null
|
| 11 |
+
dataloader_num_workers: 0
|
| 12 |
+
dataset_config_name: null
|
| 13 |
+
dataset_name: lambdalabs/naruto-blip-captions
|
| 14 |
+
enable_npu_flash_attention: false
|
| 15 |
+
enable_xformers_memory_efficient_attention: false
|
| 16 |
+
gradient_accumulation_steps: 1
|
| 17 |
+
gradient_checkpointing: false
|
| 18 |
+
hub_model_id: null
|
| 19 |
+
hub_token: null
|
| 20 |
+
image_column: image
|
| 21 |
+
learning_rate: 0.0001
|
| 22 |
+
local_rank: -1
|
| 23 |
+
logging_dir: logs
|
| 24 |
+
lr_scheduler: constant
|
| 25 |
+
lr_warmup_steps: 0
|
| 26 |
+
max_grad_norm: 1.0
|
| 27 |
+
max_train_samples: null
|
| 28 |
+
max_train_steps: 10
|
| 29 |
+
mixed_precision: fp16
|
| 30 |
+
noise_offset: 0
|
| 31 |
+
num_train_epochs: 1
|
| 32 |
+
num_validation_images: 4
|
| 33 |
+
output_dir: test
|
| 34 |
+
prediction_type: null
|
| 35 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
| 36 |
+
pretrained_vae_model_name_or_path: null
|
| 37 |
+
proportion_empty_prompts: 0
|
| 38 |
+
push_to_hub: true
|
| 39 |
+
random_flip: false
|
| 40 |
+
report_to: tensorboard
|
| 41 |
+
resolution: 1024
|
| 42 |
+
resume_from_checkpoint: null
|
| 43 |
+
revision: null
|
| 44 |
+
scale_lr: false
|
| 45 |
+
seed: null
|
| 46 |
+
snr_gamma: null
|
| 47 |
+
timestep_bias_begin: 0
|
| 48 |
+
timestep_bias_end: 1000
|
| 49 |
+
timestep_bias_multiplier: 1.0
|
| 50 |
+
timestep_bias_portion: 0.25
|
| 51 |
+
timestep_bias_strategy: none
|
| 52 |
+
train_batch_size: 1
|
| 53 |
+
train_data_dir: null
|
| 54 |
+
use_8bit_adam: false
|
| 55 |
+
use_ema: false
|
| 56 |
+
validation_epochs: 1
|
| 57 |
+
validation_prompt: null
|
| 58 |
+
variant: null
|
logs/text2image-fine-tune-sdxl/1731336010.2398946/events.out.tfevents.1731336010.scene-gen-ai-v4-0.812.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d15a85df5ad4eb66c9b46d6becd4f1f43ec59a1dc6b610142fc46ff91812047
|
| 3 |
+
size 2719
|
logs/text2image-fine-tune-sdxl/1731336010.2415638/hparams.yml
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.01
|
| 5 |
+
allow_tf32: false
|
| 6 |
+
cache_dir: null
|
| 7 |
+
caption_column: text
|
| 8 |
+
center_crop: false
|
| 9 |
+
checkpointing_steps: 10
|
| 10 |
+
checkpoints_total_limit: null
|
| 11 |
+
dataloader_num_workers: 0
|
| 12 |
+
dataset_config_name: null
|
| 13 |
+
dataset_name: lambdalabs/naruto-blip-captions
|
| 14 |
+
enable_npu_flash_attention: false
|
| 15 |
+
enable_xformers_memory_efficient_attention: false
|
| 16 |
+
gradient_accumulation_steps: 1
|
| 17 |
+
gradient_checkpointing: false
|
| 18 |
+
hub_model_id: null
|
| 19 |
+
hub_token: null
|
| 20 |
+
image_column: image
|
| 21 |
+
learning_rate: 0.0001
|
| 22 |
+
local_rank: -1
|
| 23 |
+
logging_dir: logs
|
| 24 |
+
lr_scheduler: constant
|
| 25 |
+
lr_warmup_steps: 0
|
| 26 |
+
max_grad_norm: 1.0
|
| 27 |
+
max_train_samples: null
|
| 28 |
+
max_train_steps: 10
|
| 29 |
+
mixed_precision: fp16
|
| 30 |
+
noise_offset: 0
|
| 31 |
+
num_train_epochs: 1
|
| 32 |
+
num_validation_images: 4
|
| 33 |
+
output_dir: test
|
| 34 |
+
prediction_type: null
|
| 35 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
| 36 |
+
pretrained_vae_model_name_or_path: null
|
| 37 |
+
proportion_empty_prompts: 0
|
| 38 |
+
push_to_hub: true
|
| 39 |
+
random_flip: false
|
| 40 |
+
report_to: tensorboard
|
| 41 |
+
resolution: 1024
|
| 42 |
+
resume_from_checkpoint: null
|
| 43 |
+
revision: null
|
| 44 |
+
scale_lr: false
|
| 45 |
+
seed: null
|
| 46 |
+
snr_gamma: null
|
| 47 |
+
timestep_bias_begin: 0
|
| 48 |
+
timestep_bias_end: 1000
|
| 49 |
+
timestep_bias_multiplier: 1.0
|
| 50 |
+
timestep_bias_portion: 0.25
|
| 51 |
+
timestep_bias_strategy: none
|
| 52 |
+
train_batch_size: 1
|
| 53 |
+
train_data_dir: null
|
| 54 |
+
use_8bit_adam: false
|
| 55 |
+
use_ema: false
|
| 56 |
+
validation_epochs: 10
|
| 57 |
+
validation_prompt: a cute Sundar Pichai creature
|
| 58 |
+
variant: null
|
logs/text2image-fine-tune-sdxl/1731338666.0457904/events.out.tfevents.1731338666.scene-gen-ai-v4-0.1276.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c241a59ae30bceb1c6284e4cac4db9e832c27da9c82b66bafe0c6eac95cfef7a
|
| 3 |
+
size 2719
|
logs/text2image-fine-tune-sdxl/1731338666.047378/hparams.yml
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.01
|
| 5 |
+
allow_tf32: false
|
| 6 |
+
cache_dir: null
|
| 7 |
+
caption_column: text
|
| 8 |
+
center_crop: false
|
| 9 |
+
checkpointing_steps: 10
|
| 10 |
+
checkpoints_total_limit: null
|
| 11 |
+
dataloader_num_workers: 0
|
| 12 |
+
dataset_config_name: null
|
| 13 |
+
dataset_name: lambdalabs/naruto-blip-captions
|
| 14 |
+
enable_npu_flash_attention: false
|
| 15 |
+
enable_xformers_memory_efficient_attention: false
|
| 16 |
+
gradient_accumulation_steps: 1
|
| 17 |
+
gradient_checkpointing: false
|
| 18 |
+
hub_model_id: null
|
| 19 |
+
hub_token: null
|
| 20 |
+
image_column: image
|
| 21 |
+
learning_rate: 1.0e-06
|
| 22 |
+
local_rank: -1
|
| 23 |
+
logging_dir: logs
|
| 24 |
+
lr_scheduler: constant
|
| 25 |
+
lr_warmup_steps: 0
|
| 26 |
+
max_grad_norm: 1.0
|
| 27 |
+
max_train_samples: null
|
| 28 |
+
max_train_steps: 1000
|
| 29 |
+
mixed_precision: fp16
|
| 30 |
+
noise_offset: 0
|
| 31 |
+
num_train_epochs: 1
|
| 32 |
+
num_validation_images: 4
|
| 33 |
+
output_dir: test
|
| 34 |
+
prediction_type: null
|
| 35 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
| 36 |
+
pretrained_vae_model_name_or_path: null
|
| 37 |
+
proportion_empty_prompts: 0
|
| 38 |
+
push_to_hub: true
|
| 39 |
+
random_flip: false
|
| 40 |
+
report_to: tensorboard
|
| 41 |
+
resolution: 1024
|
| 42 |
+
resume_from_checkpoint: null
|
| 43 |
+
revision: null
|
| 44 |
+
scale_lr: false
|
| 45 |
+
seed: null
|
| 46 |
+
snr_gamma: null
|
| 47 |
+
timestep_bias_begin: 0
|
| 48 |
+
timestep_bias_end: 1000
|
| 49 |
+
timestep_bias_multiplier: 1.0
|
| 50 |
+
timestep_bias_portion: 0.25
|
| 51 |
+
timestep_bias_strategy: none
|
| 52 |
+
train_batch_size: 1
|
| 53 |
+
train_data_dir: null
|
| 54 |
+
use_8bit_adam: false
|
| 55 |
+
use_ema: false
|
| 56 |
+
validation_epochs: 10
|
| 57 |
+
validation_prompt: a cute Sundar Pichai creature
|
| 58 |
+
variant: null
|
logs/text2image-fine-tune-sdxl/1731339823.9533772/events.out.tfevents.1731339823.scene-gen-ai-v4-0.1463.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8656065ec6100a30f34a313e5cd2a9996cadc43d02011bffc79653a730fcf83c
|
| 3 |
+
size 2719
|
logs/text2image-fine-tune-sdxl/1731339823.9552855/hparams.yml
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.01
|
| 5 |
+
allow_tf32: false
|
| 6 |
+
cache_dir: null
|
| 7 |
+
caption_column: text
|
| 8 |
+
center_crop: false
|
| 9 |
+
checkpointing_steps: 1000
|
| 10 |
+
checkpoints_total_limit: null
|
| 11 |
+
dataloader_num_workers: 0
|
| 12 |
+
dataset_config_name: null
|
| 13 |
+
dataset_name: lambdalabs/naruto-blip-captions
|
| 14 |
+
enable_npu_flash_attention: false
|
| 15 |
+
enable_xformers_memory_efficient_attention: false
|
| 16 |
+
gradient_accumulation_steps: 1
|
| 17 |
+
gradient_checkpointing: false
|
| 18 |
+
hub_model_id: null
|
| 19 |
+
hub_token: null
|
| 20 |
+
image_column: image
|
| 21 |
+
learning_rate: 1.0e-06
|
| 22 |
+
local_rank: -1
|
| 23 |
+
logging_dir: logs
|
| 24 |
+
lr_scheduler: constant
|
| 25 |
+
lr_warmup_steps: 0
|
| 26 |
+
max_grad_norm: 1.0
|
| 27 |
+
max_train_samples: null
|
| 28 |
+
max_train_steps: 1000
|
| 29 |
+
mixed_precision: fp16
|
| 30 |
+
noise_offset: 0
|
| 31 |
+
num_train_epochs: 1
|
| 32 |
+
num_validation_images: 4
|
| 33 |
+
output_dir: test
|
| 34 |
+
prediction_type: null
|
| 35 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
| 36 |
+
pretrained_vae_model_name_or_path: null
|
| 37 |
+
proportion_empty_prompts: 0
|
| 38 |
+
push_to_hub: true
|
| 39 |
+
random_flip: false
|
| 40 |
+
report_to: tensorboard
|
| 41 |
+
resolution: 1024
|
| 42 |
+
resume_from_checkpoint: null
|
| 43 |
+
revision: null
|
| 44 |
+
scale_lr: false
|
| 45 |
+
seed: null
|
| 46 |
+
snr_gamma: null
|
| 47 |
+
timestep_bias_begin: 0
|
| 48 |
+
timestep_bias_end: 1000
|
| 49 |
+
timestep_bias_multiplier: 1.0
|
| 50 |
+
timestep_bias_portion: 0.25
|
| 51 |
+
timestep_bias_strategy: none
|
| 52 |
+
train_batch_size: 1
|
| 53 |
+
train_data_dir: null
|
| 54 |
+
use_8bit_adam: false
|
| 55 |
+
use_ema: false
|
| 56 |
+
validation_epochs: 1000
|
| 57 |
+
validation_prompt: a cute Sundar Pichai creature
|
| 58 |
+
variant: null
|
logs/text2image-fine-tune-sdxl/1731346828.0336745/events.out.tfevents.1731346828.scene-gen-ai-v4-0.2415.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25f37ca231959492f6a970ff9caa36307b442b405f9847dd41db8519cc103df0
|
| 3 |
+
size 2719
|
logs/text2image-fine-tune-sdxl/1731346828.035174/hparams.yml
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.01
|
| 5 |
+
allow_tf32: false
|
| 6 |
+
cache_dir: null
|
| 7 |
+
caption_column: text
|
| 8 |
+
center_crop: false
|
| 9 |
+
checkpointing_steps: 1000
|
| 10 |
+
checkpoints_total_limit: null
|
| 11 |
+
dataloader_num_workers: 0
|
| 12 |
+
dataset_config_name: null
|
| 13 |
+
dataset_name: lambdalabs/naruto-blip-captions
|
| 14 |
+
enable_npu_flash_attention: false
|
| 15 |
+
enable_xformers_memory_efficient_attention: false
|
| 16 |
+
gradient_accumulation_steps: 1
|
| 17 |
+
gradient_checkpointing: false
|
| 18 |
+
hub_model_id: null
|
| 19 |
+
hub_token: null
|
| 20 |
+
image_column: image
|
| 21 |
+
learning_rate: 1.0e-06
|
| 22 |
+
local_rank: -1
|
| 23 |
+
logging_dir: logs
|
| 24 |
+
lr_scheduler: constant
|
| 25 |
+
lr_warmup_steps: 0
|
| 26 |
+
max_grad_norm: 1.0
|
| 27 |
+
max_train_samples: null
|
| 28 |
+
max_train_steps: 1000
|
| 29 |
+
mixed_precision: fp16
|
| 30 |
+
noise_offset: 0
|
| 31 |
+
num_train_epochs: 1
|
| 32 |
+
num_validation_images: 4
|
| 33 |
+
output_dir: test
|
| 34 |
+
prediction_type: null
|
| 35 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
| 36 |
+
pretrained_vae_model_name_or_path: null
|
| 37 |
+
proportion_empty_prompts: 0
|
| 38 |
+
push_to_hub: true
|
| 39 |
+
random_flip: false
|
| 40 |
+
report_to: tensorboard
|
| 41 |
+
resolution: 1024
|
| 42 |
+
resume_from_checkpoint: null
|
| 43 |
+
revision: null
|
| 44 |
+
scale_lr: false
|
| 45 |
+
seed: null
|
| 46 |
+
snr_gamma: null
|
| 47 |
+
timestep_bias_begin: 0
|
| 48 |
+
timestep_bias_end: 1000
|
| 49 |
+
timestep_bias_multiplier: 1.0
|
| 50 |
+
timestep_bias_portion: 0.25
|
| 51 |
+
timestep_bias_strategy: none
|
| 52 |
+
train_batch_size: 1
|
| 53 |
+
train_data_dir: null
|
| 54 |
+
use_8bit_adam: false
|
| 55 |
+
use_ema: false
|
| 56 |
+
validation_epochs: 1000
|
| 57 |
+
validation_prompt: a cute Sundar Pichai creature
|
| 58 |
+
variant: null
|
logs/text2image-fine-tune-sdxl/1731352544.2337453/events.out.tfevents.1731352544.scene-gen-ai-v4-0.2709.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbca5585ae403bb56839e2b0ddef63bf9dcb107505801e7e4842018b4d63f608
|
| 3 |
+
size 2719
|
logs/text2image-fine-tune-sdxl/1731352544.2352123/hparams.yml
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.01
|
| 5 |
+
allow_tf32: false
|
| 6 |
+
cache_dir: null
|
| 7 |
+
caption_column: text
|
| 8 |
+
center_crop: false
|
| 9 |
+
checkpointing_steps: 1000
|
| 10 |
+
checkpoints_total_limit: null
|
| 11 |
+
dataloader_num_workers: 0
|
| 12 |
+
dataset_config_name: null
|
| 13 |
+
dataset_name: lambdalabs/naruto-blip-captions
|
| 14 |
+
enable_npu_flash_attention: false
|
| 15 |
+
enable_xformers_memory_efficient_attention: false
|
| 16 |
+
gradient_accumulation_steps: 1
|
| 17 |
+
gradient_checkpointing: false
|
| 18 |
+
hub_model_id: null
|
| 19 |
+
hub_token: null
|
| 20 |
+
image_column: image
|
| 21 |
+
learning_rate: 1.0e-06
|
| 22 |
+
local_rank: -1
|
| 23 |
+
logging_dir: logs
|
| 24 |
+
lr_scheduler: constant
|
| 25 |
+
lr_warmup_steps: 0
|
| 26 |
+
max_grad_norm: 1.0
|
| 27 |
+
max_train_samples: null
|
| 28 |
+
max_train_steps: 1000
|
| 29 |
+
mixed_precision: fp16
|
| 30 |
+
noise_offset: 0
|
| 31 |
+
num_train_epochs: 1
|
| 32 |
+
num_validation_images: 4
|
| 33 |
+
output_dir: test
|
| 34 |
+
prediction_type: null
|
| 35 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
| 36 |
+
pretrained_vae_model_name_or_path: null
|
| 37 |
+
proportion_empty_prompts: 0
|
| 38 |
+
push_to_hub: true
|
| 39 |
+
random_flip: false
|
| 40 |
+
report_to: tensorboard
|
| 41 |
+
resolution: 1024
|
| 42 |
+
resume_from_checkpoint: null
|
| 43 |
+
revision: null
|
| 44 |
+
scale_lr: false
|
| 45 |
+
seed: null
|
| 46 |
+
snr_gamma: null
|
| 47 |
+
timestep_bias_begin: 0
|
| 48 |
+
timestep_bias_end: 1000
|
| 49 |
+
timestep_bias_multiplier: 1.0
|
| 50 |
+
timestep_bias_portion: 0.25
|
| 51 |
+
timestep_bias_strategy: none
|
| 52 |
+
train_batch_size: 1
|
| 53 |
+
train_data_dir: null
|
| 54 |
+
use_8bit_adam: false
|
| 55 |
+
use_ema: false
|
| 56 |
+
validation_epochs: 1000
|
| 57 |
+
validation_prompt: a cute Sundar Pichai creature
|
| 58 |
+
variant: null
|
logs/text2image-fine-tune-sdxl/1731361202.666019/events.out.tfevents.1731361202.scene-gen-ai-v4-0.3445.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bf468c28f99cbf36d44cad9018ff364d98489c33f9e407dde7dddbc36b643c2
|
| 3 |
+
size 2707
|
logs/text2image-fine-tune-sdxl/1731361202.6674397/hparams.yml
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.01
|
| 5 |
+
allow_tf32: false
|
| 6 |
+
cache_dir: null
|
| 7 |
+
caption_column: text
|
| 8 |
+
center_crop: false
|
| 9 |
+
checkpointing_steps: 1000
|
| 10 |
+
checkpoints_total_limit: null
|
| 11 |
+
dataloader_num_workers: 0
|
| 12 |
+
dataset_config_name: null
|
| 13 |
+
dataset_name: Brvcket/sdxl-lights
|
| 14 |
+
enable_npu_flash_attention: false
|
| 15 |
+
enable_xformers_memory_efficient_attention: false
|
| 16 |
+
gradient_accumulation_steps: 1
|
| 17 |
+
gradient_checkpointing: false
|
| 18 |
+
hub_model_id: null
|
| 19 |
+
hub_token: null
|
| 20 |
+
image_column: image
|
| 21 |
+
learning_rate: 1.0e-06
|
| 22 |
+
local_rank: -1
|
| 23 |
+
logging_dir: logs
|
| 24 |
+
lr_scheduler: constant
|
| 25 |
+
lr_warmup_steps: 0
|
| 26 |
+
max_grad_norm: 1.0
|
| 27 |
+
max_train_samples: null
|
| 28 |
+
max_train_steps: 1000
|
| 29 |
+
mixed_precision: fp16
|
| 30 |
+
noise_offset: 0
|
| 31 |
+
num_train_epochs: 1
|
| 32 |
+
num_validation_images: 4
|
| 33 |
+
output_dir: test
|
| 34 |
+
prediction_type: null
|
| 35 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
| 36 |
+
pretrained_vae_model_name_or_path: null
|
| 37 |
+
proportion_empty_prompts: 0
|
| 38 |
+
push_to_hub: true
|
| 39 |
+
random_flip: false
|
| 40 |
+
report_to: tensorboard
|
| 41 |
+
resolution: 1024
|
| 42 |
+
resume_from_checkpoint: null
|
| 43 |
+
revision: null
|
| 44 |
+
scale_lr: false
|
| 45 |
+
seed: null
|
| 46 |
+
snr_gamma: null
|
| 47 |
+
timestep_bias_begin: 0
|
| 48 |
+
timestep_bias_end: 1000
|
| 49 |
+
timestep_bias_multiplier: 1.0
|
| 50 |
+
timestep_bias_portion: 0.25
|
| 51 |
+
timestep_bias_strategy: none
|
| 52 |
+
train_batch_size: 1
|
| 53 |
+
train_data_dir: null
|
| 54 |
+
use_8bit_adam: false
|
| 55 |
+
use_ema: false
|
| 56 |
+
validation_epochs: 1000
|
| 57 |
+
validation_prompt: a cute Sundar Pichai creature
|
| 58 |
+
variant: null
|
logs/text2image-fine-tune-sdxl/1731412552.530759/events.out.tfevents.1731412552.scene-gen-ai-v4-0.4068.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83466c78984ab7e46211f0a2239b4df6465be268ae1d1969ae83138c0908f194
|
| 3 |
+
size 2707
|
logs/text2image-fine-tune-sdxl/1731412552.5325375/hparams.yml
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.01
|
| 5 |
+
allow_tf32: false
|
| 6 |
+
cache_dir: null
|
| 7 |
+
caption_column: text
|
| 8 |
+
center_crop: false
|
| 9 |
+
checkpointing_steps: 1000
|
| 10 |
+
checkpoints_total_limit: null
|
| 11 |
+
dataloader_num_workers: 0
|
| 12 |
+
dataset_config_name: null
|
| 13 |
+
dataset_name: Brvcket/sdxl-lights
|
| 14 |
+
enable_npu_flash_attention: false
|
| 15 |
+
enable_xformers_memory_efficient_attention: false
|
| 16 |
+
gradient_accumulation_steps: 1
|
| 17 |
+
gradient_checkpointing: false
|
| 18 |
+
hub_model_id: null
|
| 19 |
+
hub_token: null
|
| 20 |
+
image_column: image
|
| 21 |
+
learning_rate: 1.0e-06
|
| 22 |
+
local_rank: -1
|
| 23 |
+
logging_dir: logs
|
| 24 |
+
lr_scheduler: constant
|
| 25 |
+
lr_warmup_steps: 0
|
| 26 |
+
max_grad_norm: 1.0
|
| 27 |
+
max_train_samples: null
|
| 28 |
+
max_train_steps: 1000
|
| 29 |
+
mixed_precision: fp16
|
| 30 |
+
noise_offset: 0
|
| 31 |
+
num_train_epochs: 1
|
| 32 |
+
num_validation_images: 4
|
| 33 |
+
output_dir: test
|
| 34 |
+
prediction_type: null
|
| 35 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
| 36 |
+
pretrained_vae_model_name_or_path: null
|
| 37 |
+
proportion_empty_prompts: 0
|
| 38 |
+
push_to_hub: true
|
| 39 |
+
random_flip: false
|
| 40 |
+
report_to: tensorboard
|
| 41 |
+
resolution: 1024
|
| 42 |
+
resume_from_checkpoint: null
|
| 43 |
+
revision: null
|
| 44 |
+
scale_lr: false
|
| 45 |
+
seed: null
|
| 46 |
+
snr_gamma: null
|
| 47 |
+
timestep_bias_begin: 0
|
| 48 |
+
timestep_bias_end: 1000
|
| 49 |
+
timestep_bias_multiplier: 1.0
|
| 50 |
+
timestep_bias_portion: 0.25
|
| 51 |
+
timestep_bias_strategy: none
|
| 52 |
+
train_batch_size: 1
|
| 53 |
+
train_data_dir: null
|
| 54 |
+
use_8bit_adam: false
|
| 55 |
+
use_ema: false
|
| 56 |
+
validation_epochs: 1000
|
| 57 |
+
validation_prompt: a cute Sundar Pichai creature
|
| 58 |
+
variant: null
|
logs/text2image-fine-tune-sdxl/events.out.tfevents.1731332400.scene-gen-ai-v4-0.540.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9e0664ed7cfdcacde055ed377ec05084fe8000277a2423ece170e537a4f392a
|
| 3 |
+
size 568
|
logs/text2image-fine-tune-sdxl/events.out.tfevents.1731336010.scene-gen-ai-v4-0.812.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47d79a1a6468549cc4cb7892cda2203c3aae20a008791c7684000ad8f6f12d55
|
| 3 |
+
size 25246
|
logs/text2image-fine-tune-sdxl/events.out.tfevents.1731338665.scene-gen-ai-v4-0.1276.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34c3cfadc3f271e245984ab9a7fb8378b29b580cfc8e06dfbc730755ccc2a4cd
|
| 3 |
+
size 88
|