Upload folder using huggingface_hub
Browse files
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
assets/banner_0_0_6.png filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -3,6 +3,7 @@ license: apache-2.0
|
|
| 3 |
library_name: diffusers
|
| 4 |
pipeline_tag: text-to-image
|
| 5 |
---
|
|
|
|
| 6 |
<div style="color: red;">
|
| 7 |
|
| 8 |
# <span style="color: red;"> Not Ready </span>
|
|
@@ -13,11 +14,13 @@ feel free, but it will change as I continue to develop it. I plan to do many upd
|
|
| 13 |
</div>
|
| 14 |
|
| 15 |
## What is this?
|
|
|
|
| 16 |
[FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) is an amazing distilled model with an apache 2.0 license. However, it is not finetunable. LoRAs, IP adapters, control nets, etc, cannot be trained on it
|
| 17 |
because it is distilled. The goal of this project is to finetune a non-distilled version of it that can be used as a training base to train adapters for FLUX.1-schnell.
|
| 18 |
|
| 19 |
## Current Issues
|
|
|
|
| 20 |
Since we are breaking the distillation, this model will need many steps and guidance to produce good results. Currently, this model, like the schnell version, does not
|
| 21 |
have guidance embeddings. Because of this (and possible other factors) images generated with this model will not look great. However, this hopefully will not affect training,
|
| 22 |
since guidance is not used during training. The things trained on this model are intended to be used on the schnell version anyway. I am working on training guidance
|
| 23 |
-
embeddings for it, but hopefully it will work as a training base without them.
|
|
|
|
| 3 |
library_name: diffusers
|
| 4 |
pipeline_tag: text-to-image
|
| 5 |
---
|
| 6 |
+
|
| 7 |
<div style="color: red;">
|
| 8 |
|
| 9 |
# <span style="color: red;"> Not Ready </span>
|
|
|
|
| 14 |
</div>
|
| 15 |
|
| 16 |
## What is this?
|
| 17 |
+
|
| 18 |
[FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) is an amazing distilled model with an apache 2.0 license. However, it is not finetunable. LoRAs, IP adapters, control nets, etc, cannot be trained on it
|
| 19 |
because it is distilled. The goal of this project is to finetune a non-distilled version of it that can be used as a training base to train adapters for FLUX.1-schnell.
|
| 20 |
|
| 21 |
## Current Issues
|
| 22 |
+
|
| 23 |
Since we are breaking the distillation, this model will need many steps and guidance to produce good results. Currently, this model, like the schnell version, does not
|
| 24 |
have guidance embeddings. Because of this (and possible other factors) images generated with this model will not look great. However, this hopefully will not affect training,
|
| 25 |
since guidance is not used during training. The things trained on this model are intended to be used on the schnell version anyway. I am working on training guidance
|
| 26 |
+
embeddings for it, but hopefully it will work as a training base without them.
|
assets/banner_0_0_6.png
ADDED
|
Git LFS Details
|
transformer/diffusion_pytorch_model-00001-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9962580296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9870097e9820bafa003b132660cbf60281f740807c6d77b889417a4e7cbfd788
|
| 3 |
size 9962580296
|
transformer/diffusion_pytorch_model-00002-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9949328904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf3da1c1491be4a0846deb6020cfec94ec0b09dbd093195e9a5c3c53a6168fd5
|
| 3 |
size 9949328904
|
transformer/diffusion_pytorch_model-00003-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3870584832
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c38b5f137b578e7b4995740dbeb39ea794667f1bd6deda5a6b3f0c22158c2c9e
|
| 3 |
size 3870584832
|