End of training
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- README.md +39 -0
- checkpoint-1000/model.safetensors +3 -0
- checkpoint-1000/optimizer.bin +3 -0
- checkpoint-1000/random_states_0.pkl +3 -0
- checkpoint-1000/scheduler.bin +3 -0
- checkpoint-1500/model.safetensors +3 -0
- checkpoint-1500/optimizer.bin +3 -0
- checkpoint-1500/random_states_0.pkl +3 -0
- checkpoint-1500/scheduler.bin +3 -0
- checkpoint-2000/model.safetensors +3 -0
- checkpoint-2000/optimizer.bin +3 -0
- checkpoint-2000/random_states_0.pkl +3 -0
- checkpoint-2000/scheduler.bin +3 -0
- checkpoint-2500/model.safetensors +3 -0
- checkpoint-2500/optimizer.bin +3 -0
- checkpoint-2500/random_states_0.pkl +3 -0
- checkpoint-2500/scheduler.bin +3 -0
- checkpoint-3000/model.safetensors +3 -0
- checkpoint-3000/optimizer.bin +3 -0
- checkpoint-3000/random_states_0.pkl +3 -0
- checkpoint-3000/scheduler.bin +3 -0
- checkpoint-500/model.safetensors +3 -0
- checkpoint-500/optimizer.bin +3 -0
- checkpoint-500/random_states_0.pkl +3 -0
- checkpoint-500/scheduler.bin +3 -0
- feature_extractor/preprocessor_config.json +28 -0
- learned_embeds-steps-1000.safetensors +3 -0
- learned_embeds-steps-1500.safetensors +3 -0
- learned_embeds-steps-2000.safetensors +3 -0
- learned_embeds-steps-2500.safetensors +3 -0
- learned_embeds-steps-3000.safetensors +3 -0
- learned_embeds-steps-500.safetensors +3 -0
- learned_embeds.safetensors +3 -0
- logs/textual_inversion/1717439890.5880127/events.out.tfevents.1717439890.deep-gpu-11.csail.mit.edu.2063738.1 +3 -0
- logs/textual_inversion/1717439890.6113079/hparams.yml +49 -0
- logs/textual_inversion/1717439937.9958181/events.out.tfevents.1717439938.deep-gpu-11.csail.mit.edu.2063960.1 +3 -0
- logs/textual_inversion/1717439938.0201588/hparams.yml +49 -0
- logs/textual_inversion/1717597124.9829347/events.out.tfevents.1717597124.deep-gpu-11.csail.mit.edu.2359678.1 +3 -0
- logs/textual_inversion/1717597124.9979684/hparams.yml +49 -0
- logs/textual_inversion/events.out.tfevents.1717439890.deep-gpu-11.csail.mit.edu.2063738.0 +3 -0
- logs/textual_inversion/events.out.tfevents.1717439937.deep-gpu-11.csail.mit.edu.2063960.0 +3 -0
- logs/textual_inversion/events.out.tfevents.1717597124.deep-gpu-11.csail.mit.edu.2359678.0 +3 -0
- model_index.json +38 -0
- safety_checker/config.json +181 -0
- safety_checker/model.safetensors +3 -0
- scheduler/scheduler_config.json +15 -0
- text_encoder/config.json +25 -0
- text_encoder/model.safetensors +3 -0
- tokenizer/added_tokens.json +3 -0
- tokenizer/merges.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: creativeml-openrail-m
|
| 3 |
+
library_name: diffusers
|
| 4 |
+
tags:
|
| 5 |
+
- stable-diffusion
|
| 6 |
+
- stable-diffusion-diffusers
|
| 7 |
+
- text-to-image
|
| 8 |
+
- diffusers
|
| 9 |
+
- textual_inversion
|
| 10 |
+
- diffusers-training
|
| 11 |
+
base_model: CompVis/stable-diffusion-v1-4
|
| 12 |
+
inference: true
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the training script had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
# Textual inversion text2image fine-tuning - heale22/textual_inversion_chair
|
| 20 |
+
These are textual inversion adaption weights for CompVis/stable-diffusion-v1-4. You can find some example images in the following.
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
#### How to use
|
| 28 |
+
|
| 29 |
+
```python
|
| 30 |
+
# TODO: add an example code snippet for running this diffusion pipeline
|
| 31 |
+
```
|
| 32 |
+
|
| 33 |
+
#### Limitations and bias
|
| 34 |
+
|
| 35 |
+
[TODO: provide examples of latent issues and potential remediations]
|
| 36 |
+
|
| 37 |
+
## Training details
|
| 38 |
+
|
| 39 |
+
[TODO: describe the data used to train the model]
|
checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6be90ea11450dc086c5120f7d6eab1e5c5ddd74e11705691d17839c543e4d63
|
| 3 |
+
size 492268952
|
checkpoint-1000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc65de929799bcb0f25c7729923288eb2f47c1aa76bb7c5ab814e5f255c01dfa
|
| 3 |
+
size 303570914
|
checkpoint-1000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d8903b959e4ff31e104e3621bb6511cb549c03e0fd94d1b6cfc63356a446fff
|
| 3 |
+
size 14344
|
checkpoint-1000/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f0d829441992ff2ab1f7502a3a94afc011706461052e42e18e5b963678527c4
|
| 3 |
+
size 1000
|
checkpoint-1500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a65622bc5b9daff30117b571ccf0d69a4c6b8383fc51e62127b6f9f62456b08e
|
| 3 |
+
size 492268952
|
checkpoint-1500/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8f0097400b2797d8a4a7f5e6781ad6b8474f2c9d35698a34c514851d4f37408
|
| 3 |
+
size 303570914
|
checkpoint-1500/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ac6a0434b32b6fcceb5489ec34577e660687ebe7c107e00a654f8221c2503db
|
| 3 |
+
size 14344
|
checkpoint-1500/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0746407d5e6c8d929c4e940db747c88272550cab75cfb856468297d71d7802ca
|
| 3 |
+
size 1000
|
checkpoint-2000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:210c90d05c123916cb19d0259969914dc3ee65f031d328c612458d42279ea463
|
| 3 |
+
size 492268952
|
checkpoint-2000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5eb58bf69d961b3a33a5f7734d5633a76855f555d0ce5325cf08b0429278aa5e
|
| 3 |
+
size 303570914
|
checkpoint-2000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2ab04e90d5f438c7f8e227d09c96ef49c04c91181ccb9ebb400768bfaa1f07d
|
| 3 |
+
size 14344
|
checkpoint-2000/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5484c6ff4bca55d86f0d54575371a1f3b26246b4ff863161800c9be8539d8c77
|
| 3 |
+
size 1000
|
checkpoint-2500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e12923ea1831ed36d1453baf77722c2f9d9c981b442bec06e567b7740a08f59d
|
| 3 |
+
size 492268952
|
checkpoint-2500/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9121ea18156ee0fd1afbb2597e9f73e4e60ede2c5a309785cd7f812537d927c
|
| 3 |
+
size 303570914
|
checkpoint-2500/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:415132f3d1c48241178d1fc822f4afaf1c6819471e6c276fcae9c8bc79041692
|
| 3 |
+
size 14408
|
checkpoint-2500/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bb1a67b9696a2697693774a6f09d8186c78e37cff7896931a3632a6822f70b9
|
| 3 |
+
size 1000
|
checkpoint-3000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fd28ce3f11f2210d22a57d967006ea527b1ffacd76bf10814323e573778db69
|
| 3 |
+
size 492268952
|
checkpoint-3000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c1f2ce299d1a316a5a521e96e00a68930ea69db7462cac470ae809c33b268a1
|
| 3 |
+
size 303570914
|
checkpoint-3000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9029486671afc5cbbbdf40f745999aaaa18861412d10b343e47dce865fe09b84
|
| 3 |
+
size 14344
|
checkpoint-3000/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ed1284c2bacec58dd33ce8bc7070e7691d6d084b54330b85bacc37784d59cee
|
| 3 |
+
size 1000
|
checkpoint-500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6a0a97ebdbbee42e59e23684185f5025df27721aa0bf8d38e01c9e39d5b1ba9
|
| 3 |
+
size 492268952
|
checkpoint-500/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01d7f0c0becf4e24046fa35cdc820803925be27105c4dbcc7a7d3464732329f1
|
| 3 |
+
size 303570914
|
checkpoint-500/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f669cc45cec086d77445d553b85a9f4a9053e3cdd326973eaa0b4156930883f5
|
| 3 |
+
size 14344
|
checkpoint-500/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cad514bb36617120f19b7cde3b36a22bc8becf6cc6cfb2166811645c215cccb
|
| 3 |
+
size 1000
|
feature_extractor/preprocessor_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 224,
|
| 4 |
+
"width": 224
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": true,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"feature_extractor_type": "CLIPFeatureExtractor",
|
| 12 |
+
"image_mean": [
|
| 13 |
+
0.48145466,
|
| 14 |
+
0.4578275,
|
| 15 |
+
0.40821073
|
| 16 |
+
],
|
| 17 |
+
"image_processor_type": "CLIPImageProcessor",
|
| 18 |
+
"image_std": [
|
| 19 |
+
0.26862954,
|
| 20 |
+
0.26130258,
|
| 21 |
+
0.27577711
|
| 22 |
+
],
|
| 23 |
+
"resample": 3,
|
| 24 |
+
"rescale_factor": 0.00392156862745098,
|
| 25 |
+
"size": {
|
| 26 |
+
"shortest_edge": 224
|
| 27 |
+
}
|
| 28 |
+
}
|
learned_embeds-steps-1000.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f561f1eb5a6a2b369410b227555889aa61f35a85b9561fc0fda2a79f8d9b6247
|
| 3 |
+
size 3184
|
learned_embeds-steps-1500.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:454c3608b12242793ef42c2859857688e90cb02d26313891981b572f0ad4e64c
|
| 3 |
+
size 3184
|
learned_embeds-steps-2000.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1042ba5854c9f4de00f87d8a9ae22f9acb0dca46e7768298b920160489eb269
|
| 3 |
+
size 3184
|
learned_embeds-steps-2500.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a623e293ceb23a2ea7852556d48ec2c861cecc4b8e5943a05c1e9dd304ecdfde
|
| 3 |
+
size 3184
|
learned_embeds-steps-3000.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02768258c1d56b86121eb794a8bbd21dde3b89149d45c81bbdac0b9929fcc496
|
| 3 |
+
size 3184
|
learned_embeds-steps-500.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:366c8ab95337ee4f1350ed1f388ada5407b5cc4db14a5f01d898365400c6d1cd
|
| 3 |
+
size 3184
|
learned_embeds.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02768258c1d56b86121eb794a8bbd21dde3b89149d45c81bbdac0b9929fcc496
|
| 3 |
+
size 3184
|
logs/textual_inversion/1717439890.5880127/events.out.tfevents.1717439890.deep-gpu-11.csail.mit.edu.2063738.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30e3f5bdfbd680941b5abd655e01201a3055ceaa4b1693a3424129d431c39066
|
| 3 |
+
size 2474
|
logs/textual_inversion/1717439890.6113079/hparams.yml
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
center_crop: false
|
| 7 |
+
checkpointing_steps: 500
|
| 8 |
+
checkpoints_total_limit: null
|
| 9 |
+
dataloader_num_workers: 0
|
| 10 |
+
enable_xformers_memory_efficient_attention: false
|
| 11 |
+
gradient_accumulation_steps: 4
|
| 12 |
+
gradient_checkpointing: false
|
| 13 |
+
hub_model_id: null
|
| 14 |
+
hub_token: null
|
| 15 |
+
initializer_token: chair
|
| 16 |
+
learnable_property: object
|
| 17 |
+
learning_rate: 0.002
|
| 18 |
+
local_rank: -1
|
| 19 |
+
logging_dir: logs
|
| 20 |
+
lr_num_cycles: 1
|
| 21 |
+
lr_scheduler: constant
|
| 22 |
+
lr_warmup_steps: 0
|
| 23 |
+
max_train_steps: 3000
|
| 24 |
+
mixed_precision: 'no'
|
| 25 |
+
model_name_unique: compvis-word_chair-method_noxattn-sg_3-ng_1-iter_1000-lr_1e-05
|
| 26 |
+
no_safe_serialization: false
|
| 27 |
+
num_train_epochs: 24
|
| 28 |
+
num_validation_images: 4
|
| 29 |
+
num_vectors: 1
|
| 30 |
+
output_dir: textual_inversion_chair
|
| 31 |
+
placeholder_token: <vic-chair>
|
| 32 |
+
pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
|
| 33 |
+
push_to_hub: true
|
| 34 |
+
repeats: 100
|
| 35 |
+
report_to: tensorboard
|
| 36 |
+
resolution: 512
|
| 37 |
+
resume_from_checkpoint: null
|
| 38 |
+
revision: null
|
| 39 |
+
save_as_full_pipeline: false
|
| 40 |
+
save_steps: 500
|
| 41 |
+
scale_lr: true
|
| 42 |
+
seed: null
|
| 43 |
+
tokenizer_name: null
|
| 44 |
+
train_batch_size: 1
|
| 45 |
+
train_data_dir: ./examples/textual_inversion/chair_images
|
| 46 |
+
validation_epochs: null
|
| 47 |
+
validation_prompt: null
|
| 48 |
+
validation_steps: 100
|
| 49 |
+
variant: null
|
logs/textual_inversion/1717439937.9958181/events.out.tfevents.1717439938.deep-gpu-11.csail.mit.edu.2063960.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dca39eb37af713f2eff41d7d844d11d40565aaac33142ae2627dbecbb53a0e9a
|
| 3 |
+
size 2474
|
logs/textual_inversion/1717439938.0201588/hparams.yml
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
center_crop: false
|
| 7 |
+
checkpointing_steps: 500
|
| 8 |
+
checkpoints_total_limit: null
|
| 9 |
+
dataloader_num_workers: 0
|
| 10 |
+
enable_xformers_memory_efficient_attention: false
|
| 11 |
+
gradient_accumulation_steps: 4
|
| 12 |
+
gradient_checkpointing: false
|
| 13 |
+
hub_model_id: null
|
| 14 |
+
hub_token: null
|
| 15 |
+
initializer_token: chair
|
| 16 |
+
learnable_property: object
|
| 17 |
+
learning_rate: 0.002
|
| 18 |
+
local_rank: -1
|
| 19 |
+
logging_dir: logs
|
| 20 |
+
lr_num_cycles: 1
|
| 21 |
+
lr_scheduler: constant
|
| 22 |
+
lr_warmup_steps: 0
|
| 23 |
+
max_train_steps: 3000
|
| 24 |
+
mixed_precision: 'no'
|
| 25 |
+
model_name_unique: compvis-word_chair-method_noxattn-sg_3-ng_1-iter_1000-lr_1e-05
|
| 26 |
+
no_safe_serialization: false
|
| 27 |
+
num_train_epochs: 24
|
| 28 |
+
num_validation_images: 4
|
| 29 |
+
num_vectors: 1
|
| 30 |
+
output_dir: textual_inversion_chair
|
| 31 |
+
placeholder_token: <vic-chair>
|
| 32 |
+
pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
|
| 33 |
+
push_to_hub: true
|
| 34 |
+
repeats: 100
|
| 35 |
+
report_to: tensorboard
|
| 36 |
+
resolution: 512
|
| 37 |
+
resume_from_checkpoint: null
|
| 38 |
+
revision: null
|
| 39 |
+
save_as_full_pipeline: false
|
| 40 |
+
save_steps: 500
|
| 41 |
+
scale_lr: true
|
| 42 |
+
seed: null
|
| 43 |
+
tokenizer_name: null
|
| 44 |
+
train_batch_size: 1
|
| 45 |
+
train_data_dir: ./examples/textual_inversion/chair_images
|
| 46 |
+
validation_epochs: null
|
| 47 |
+
validation_prompt: null
|
| 48 |
+
validation_steps: 100
|
| 49 |
+
variant: null
|
logs/textual_inversion/1717597124.9829347/events.out.tfevents.1717597124.deep-gpu-11.csail.mit.edu.2359678.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:974c4353959b24ef74095e85c7f4250bccf8037e363d0a954a2bd64c1c49a6ca
|
| 3 |
+
size 2474
|
logs/textual_inversion/1717597124.9979684/hparams.yml
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
center_crop: false
|
| 7 |
+
checkpointing_steps: 500
|
| 8 |
+
checkpoints_total_limit: null
|
| 9 |
+
dataloader_num_workers: 0
|
| 10 |
+
enable_xformers_memory_efficient_attention: false
|
| 11 |
+
gradient_accumulation_steps: 4
|
| 12 |
+
gradient_checkpointing: false
|
| 13 |
+
hub_model_id: null
|
| 14 |
+
hub_token: null
|
| 15 |
+
initializer_token: chair
|
| 16 |
+
learnable_property: object
|
| 17 |
+
learning_rate: 0.002
|
| 18 |
+
local_rank: -1
|
| 19 |
+
logging_dir: logs
|
| 20 |
+
lr_num_cycles: 1
|
| 21 |
+
lr_scheduler: constant
|
| 22 |
+
lr_warmup_steps: 0
|
| 23 |
+
max_train_steps: 3000
|
| 24 |
+
mixed_precision: 'no'
|
| 25 |
+
model_name_unique: compvis-word_chair-method_noxattn-sg_3-ng_1-iter_1000-lr_1e-05
|
| 26 |
+
no_safe_serialization: false
|
| 27 |
+
num_train_epochs: 24
|
| 28 |
+
num_validation_images: 4
|
| 29 |
+
num_vectors: 1
|
| 30 |
+
output_dir: textual_inversion_chair
|
| 31 |
+
placeholder_token: <vic-chair>
|
| 32 |
+
pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
|
| 33 |
+
push_to_hub: true
|
| 34 |
+
repeats: 100
|
| 35 |
+
report_to: tensorboard
|
| 36 |
+
resolution: 512
|
| 37 |
+
resume_from_checkpoint: null
|
| 38 |
+
revision: null
|
| 39 |
+
save_as_full_pipeline: false
|
| 40 |
+
save_steps: 500
|
| 41 |
+
scale_lr: true
|
| 42 |
+
seed: null
|
| 43 |
+
tokenizer_name: null
|
| 44 |
+
train_batch_size: 1
|
| 45 |
+
train_data_dir: ./examples/textual_inversion/chair_images
|
| 46 |
+
validation_epochs: null
|
| 47 |
+
validation_prompt: null
|
| 48 |
+
validation_steps: 100
|
| 49 |
+
variant: null
|
logs/textual_inversion/events.out.tfevents.1717439890.deep-gpu-11.csail.mit.edu.2063738.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6441ca74c2e1e9e0c5117172d3bebfc190528ba0a66212bea80ad0a212df47cb
|
| 3 |
+
size 2044
|
logs/textual_inversion/events.out.tfevents.1717439937.deep-gpu-11.csail.mit.edu.2063960.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f40a51643250fd61c671152938751f8ac6bb7523e5ee9016685889253d60e6c7
|
| 3 |
+
size 136142
|
logs/textual_inversion/events.out.tfevents.1717597124.deep-gpu-11.csail.mit.edu.2359678.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c20f6083f81b7066d24e5c6397ecf437ae306281c5017d8ea8cde940d8f2c59
|
| 3 |
+
size 1007054
|
model_index.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "StableDiffusionPipeline",
|
| 3 |
+
"_diffusers_version": "0.29.0.dev0",
|
| 4 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
| 5 |
+
"feature_extractor": [
|
| 6 |
+
"transformers",
|
| 7 |
+
"CLIPImageProcessor"
|
| 8 |
+
],
|
| 9 |
+
"image_encoder": [
|
| 10 |
+
null,
|
| 11 |
+
null
|
| 12 |
+
],
|
| 13 |
+
"requires_safety_checker": true,
|
| 14 |
+
"safety_checker": [
|
| 15 |
+
"stable_diffusion",
|
| 16 |
+
"StableDiffusionSafetyChecker"
|
| 17 |
+
],
|
| 18 |
+
"scheduler": [
|
| 19 |
+
"diffusers",
|
| 20 |
+
"PNDMScheduler"
|
| 21 |
+
],
|
| 22 |
+
"text_encoder": [
|
| 23 |
+
"transformers",
|
| 24 |
+
"CLIPTextModel"
|
| 25 |
+
],
|
| 26 |
+
"tokenizer": [
|
| 27 |
+
"transformers",
|
| 28 |
+
"CLIPTokenizer"
|
| 29 |
+
],
|
| 30 |
+
"unet": [
|
| 31 |
+
"diffusers",
|
| 32 |
+
"UNet2DConditionModel"
|
| 33 |
+
],
|
| 34 |
+
"vae": [
|
| 35 |
+
"diffusers",
|
| 36 |
+
"AutoencoderKL"
|
| 37 |
+
]
|
| 38 |
+
}
|
safety_checker/config.json
ADDED
|
@@ -0,0 +1,181 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_commit_hash": "133a221b8aa7292a167afc5127cb63fb5005638b",
|
| 3 |
+
"_name_or_path": "/mnt/xfs/home/alexh22/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/safety_checker",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"StableDiffusionSafetyChecker"
|
| 6 |
+
],
|
| 7 |
+
"initializer_factor": 1.0,
|
| 8 |
+
"logit_scale_init_value": 2.6592,
|
| 9 |
+
"model_type": "clip",
|
| 10 |
+
"projection_dim": 768,
|
| 11 |
+
"text_config": {
|
| 12 |
+
"_name_or_path": "",
|
| 13 |
+
"add_cross_attention": false,
|
| 14 |
+
"architectures": null,
|
| 15 |
+
"attention_dropout": 0.0,
|
| 16 |
+
"bad_words_ids": null,
|
| 17 |
+
"begin_suppress_tokens": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"cross_attention_hidden_size": null,
|
| 21 |
+
"decoder_start_token_id": null,
|
| 22 |
+
"diversity_penalty": 0.0,
|
| 23 |
+
"do_sample": false,
|
| 24 |
+
"dropout": 0.0,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "quick_gelu",
|
| 33 |
+
"hidden_size": 768,
|
| 34 |
+
"id2label": {
|
| 35 |
+
"0": "LABEL_0",
|
| 36 |
+
"1": "LABEL_1"
|
| 37 |
+
},
|
| 38 |
+
"initializer_factor": 1.0,
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 77,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "clip_text_model",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"prefix": null,
|
| 64 |
+
"problem_type": null,
|
| 65 |
+
"projection_dim": 512,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"suppress_tokens": null,
|
| 73 |
+
"task_specific_params": null,
|
| 74 |
+
"temperature": 1.0,
|
| 75 |
+
"tf_legacy_loss": false,
|
| 76 |
+
"tie_encoder_decoder": false,
|
| 77 |
+
"tie_word_embeddings": true,
|
| 78 |
+
"tokenizer_class": null,
|
| 79 |
+
"top_k": 50,
|
| 80 |
+
"top_p": 1.0,
|
| 81 |
+
"torch_dtype": null,
|
| 82 |
+
"torchscript": false,
|
| 83 |
+
"transformers_version": "4.25.1",
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"vocab_size": 49408
|
| 87 |
+
},
|
| 88 |
+
"text_config_dict": {
|
| 89 |
+
"hidden_size": 768,
|
| 90 |
+
"intermediate_size": 3072,
|
| 91 |
+
"num_attention_heads": 12,
|
| 92 |
+
"num_hidden_layers": 12
|
| 93 |
+
},
|
| 94 |
+
"torch_dtype": "float32",
|
| 95 |
+
"transformers_version": null,
|
| 96 |
+
"vision_config": {
|
| 97 |
+
"_name_or_path": "",
|
| 98 |
+
"add_cross_attention": false,
|
| 99 |
+
"architectures": null,
|
| 100 |
+
"attention_dropout": 0.0,
|
| 101 |
+
"bad_words_ids": null,
|
| 102 |
+
"begin_suppress_tokens": null,
|
| 103 |
+
"bos_token_id": null,
|
| 104 |
+
"chunk_size_feed_forward": 0,
|
| 105 |
+
"cross_attention_hidden_size": null,
|
| 106 |
+
"decoder_start_token_id": null,
|
| 107 |
+
"diversity_penalty": 0.0,
|
| 108 |
+
"do_sample": false,
|
| 109 |
+
"dropout": 0.0,
|
| 110 |
+
"early_stopping": false,
|
| 111 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 112 |
+
"eos_token_id": null,
|
| 113 |
+
"exponential_decay_length_penalty": null,
|
| 114 |
+
"finetuning_task": null,
|
| 115 |
+
"forced_bos_token_id": null,
|
| 116 |
+
"forced_eos_token_id": null,
|
| 117 |
+
"hidden_act": "quick_gelu",
|
| 118 |
+
"hidden_size": 1024,
|
| 119 |
+
"id2label": {
|
| 120 |
+
"0": "LABEL_0",
|
| 121 |
+
"1": "LABEL_1"
|
| 122 |
+
},
|
| 123 |
+
"image_size": 224,
|
| 124 |
+
"initializer_factor": 1.0,
|
| 125 |
+
"initializer_range": 0.02,
|
| 126 |
+
"intermediate_size": 4096,
|
| 127 |
+
"is_decoder": false,
|
| 128 |
+
"is_encoder_decoder": false,
|
| 129 |
+
"label2id": {
|
| 130 |
+
"LABEL_0": 0,
|
| 131 |
+
"LABEL_1": 1
|
| 132 |
+
},
|
| 133 |
+
"layer_norm_eps": 1e-05,
|
| 134 |
+
"length_penalty": 1.0,
|
| 135 |
+
"max_length": 20,
|
| 136 |
+
"min_length": 0,
|
| 137 |
+
"model_type": "clip_vision_model",
|
| 138 |
+
"no_repeat_ngram_size": 0,
|
| 139 |
+
"num_attention_heads": 16,
|
| 140 |
+
"num_beam_groups": 1,
|
| 141 |
+
"num_beams": 1,
|
| 142 |
+
"num_channels": 3,
|
| 143 |
+
"num_hidden_layers": 24,
|
| 144 |
+
"num_return_sequences": 1,
|
| 145 |
+
"output_attentions": false,
|
| 146 |
+
"output_hidden_states": false,
|
| 147 |
+
"output_scores": false,
|
| 148 |
+
"pad_token_id": null,
|
| 149 |
+
"patch_size": 14,
|
| 150 |
+
"prefix": null,
|
| 151 |
+
"problem_type": null,
|
| 152 |
+
"projection_dim": 512,
|
| 153 |
+
"pruned_heads": {},
|
| 154 |
+
"remove_invalid_values": false,
|
| 155 |
+
"repetition_penalty": 1.0,
|
| 156 |
+
"return_dict": true,
|
| 157 |
+
"return_dict_in_generate": false,
|
| 158 |
+
"sep_token_id": null,
|
| 159 |
+
"suppress_tokens": null,
|
| 160 |
+
"task_specific_params": null,
|
| 161 |
+
"temperature": 1.0,
|
| 162 |
+
"tf_legacy_loss": false,
|
| 163 |
+
"tie_encoder_decoder": false,
|
| 164 |
+
"tie_word_embeddings": true,
|
| 165 |
+
"tokenizer_class": null,
|
| 166 |
+
"top_k": 50,
|
| 167 |
+
"top_p": 1.0,
|
| 168 |
+
"torch_dtype": null,
|
| 169 |
+
"torchscript": false,
|
| 170 |
+
"transformers_version": "4.25.1",
|
| 171 |
+
"typical_p": 1.0,
|
| 172 |
+
"use_bfloat16": false
|
| 173 |
+
},
|
| 174 |
+
"vision_config_dict": {
|
| 175 |
+
"hidden_size": 1024,
|
| 176 |
+
"intermediate_size": 4096,
|
| 177 |
+
"num_attention_heads": 16,
|
| 178 |
+
"num_hidden_layers": 24,
|
| 179 |
+
"patch_size": 14
|
| 180 |
+
}
|
| 181 |
+
}
|
safety_checker/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11cfe53105625af8c00faac32a430626641cce686454f3c39d837f14397d858b
|
| 3 |
+
size 1215981832
|
scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "PNDMScheduler",
|
| 3 |
+
"_diffusers_version": "0.29.0.dev0",
|
| 4 |
+
"beta_end": 0.012,
|
| 5 |
+
"beta_schedule": "scaled_linear",
|
| 6 |
+
"beta_start": 0.00085,
|
| 7 |
+
"clip_sample": false,
|
| 8 |
+
"num_train_timesteps": 1000,
|
| 9 |
+
"prediction_type": "epsilon",
|
| 10 |
+
"set_alpha_to_one": false,
|
| 11 |
+
"skip_prk_steps": true,
|
| 12 |
+
"steps_offset": 1,
|
| 13 |
+
"timestep_spacing": "leading",
|
| 14 |
+
"trained_betas": null
|
| 15 |
+
}
|
text_encoder/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "CompVis/stable-diffusion-v1-4",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPTextModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"dropout": 0.0,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "quick_gelu",
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_factor": 1.0,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 77,
|
| 17 |
+
"model_type": "clip_text_model",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"projection_dim": 512,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.25.1",
|
| 24 |
+
"vocab_size": 49409
|
| 25 |
+
}
|
text_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fd28ce3f11f2210d22a57d967006ea527b1ffacd76bf10814323e573778db69
|
| 3 |
+
size 492268952
|
tokenizer/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<vic-chair>": 49408
|
| 3 |
+
}
|
tokenizer/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|