ostris commited on
Commit
6b3c303
1 Parent(s): e1df254

Upload folder using huggingface_hub

Browse files
.DS_Store ADDED
Binary file (6.15 kB). View file
 
._.DS_Store ADDED
Binary file (4.1 kB). View file
 
.gitattributes CHANGED
@@ -36,3 +36,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
36
  assets/banner_0_0_6.png filter=lfs diff=lfs merge=lfs -text
37
  assets/banner_0_0_8.png filter=lfs diff=lfs merge=lfs -text
38
  assets/banner_0_0_9.png filter=lfs diff=lfs merge=lfs -text
 
 
 
 
36
  assets/banner_0_0_6.png filter=lfs diff=lfs merge=lfs -text
37
  assets/banner_0_0_8.png filter=lfs diff=lfs merge=lfs -text
38
  assets/banner_0_0_9.png filter=lfs diff=lfs merge=lfs -text
39
+ assets/banner_0_1_0-0.png filter=lfs diff=lfs merge=lfs -text
40
+ assets/banner_0_1_0-1.png filter=lfs diff=lfs merge=lfs -text
41
+ assets/banner_0_1_0-3.png filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -4,16 +4,25 @@ library_name: diffusers
4
  pipeline_tag: text-to-image
5
  ---
6
 
7
- <img src="https://huggingface.co/ostris/OpenFLUX.1/resolve/main/assets/banner_0_0_9.png" style="max-width: 100%;">
8
 
9
- <div style="color: red;">
10
 
11
- # <span style="color: red;"> Not Ready </span>
12
 
13
- This is a WIP. It is nearing a state I am going to call "early pre alpha". You are welcome to start messing with it at this point, but it still has a ways to go before it is ready for people to start finetuning on it. New updates are being pushed every few days as it continues to train. I will update this message when it is ready for that.
14
 
15
  </div>
16
 
 
 
17
  ## What is this?
18
 
19
- This project started as a way to train adapters for the [FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) model. But has evolved over time. The purpose of this project now, is to create an open source version of FLUX.1 that uses classic CFG and is finetunable for the community. Since it requires CFG, it will require a different pipeline than the original FLUX.1. This pipeline can be found in open_flux_pipeline.py in this repo.
 
 
 
 
 
 
 
 
4
  pipeline_tag: text-to-image
5
  ---
6
 
7
+ <img src="https://huggingface.co/ostris/OpenFLUX.1/resolve/main/assets/banner_0_1_0-0.png" style="max-width: 100%;">
8
 
9
+ <div style="color: #f0b800;">
10
 
11
+ # <span style="color: #f0b800;"> Beta Version v0.1.0 </span>
12
 
13
+ After numerous iterations and spending way too much of my own money on compute to train this, I think it is finally at the point I am happy to consider it a beta. I am still going to continue to train it, but the distillation has been mostly trained out of it at this point. So phase 1 is complete. Feel free to use it and fine tune it, but be aware that I will likely continue to update it.
14
 
15
  </div>
16
 
17
+ <img src="https://huggingface.co/ostris/OpenFLUX.1/resolve/main/assets/banner_0_1_0-3.png" style="max-width: 100%;">
18
+
19
  ## What is this?
20
 
21
+ This is a fine tune of the [FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) model that has had the distillation trained out of it. Flux Schnell is licensed Apache 2.0, but it is a distilled model, meaning you cannot fine-tune it. However, it is an amazing model that can generate amazing images in 1-4 steps. This is an attempt to remove the distillation to create an open source, permissivle licensed model that can be fine tuned.
22
+
23
+ ## How to Use
24
+
25
+ Since the distillation has been fine tuned out of the model, it uses classic CFG. Since it requires CFG, it will require a different pipeline than the original FLUX.1 schnell and dev models. This pipeline can be found in open_flux_pipeline.py in this repo. I will be adding example code in the next few days, but for now, a cfg of 3.5 seems to work well.
26
+
27
+
28
+ <img src="https://huggingface.co/ostris/OpenFLUX.1/resolve/main/assets/banner_0_1_0-1.png" style="max-width: 100%;">
assets/banner_0_1_0-0.png ADDED

Git LFS Details

  • SHA256: ad80aa79f63c58bb94a365a476f5f055c25fd5ff2cc152f0c074d9f779264496
  • Pointer size: 132 Bytes
  • Size of remote file: 1.59 MB
assets/banner_0_1_0-1.png ADDED

Git LFS Details

  • SHA256: 7be77f156ffdaea2b16a1b12678e599dc209c19ee8dfabb9ef046f46f3e9379e
  • Pointer size: 132 Bytes
  • Size of remote file: 1.54 MB
assets/banner_0_1_0-3.png ADDED

Git LFS Details

  • SHA256: 3a4a4f335c3f38cefd16648ce9307a8e564bdd9fb6bcbc12adfa0082f1cc4531
  • Pointer size: 132 Bytes
  • Size of remote file: 1.68 MB
transformer/diffusion_pytorch_model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0691bdb55f1dcca1935ca87c1b0ee888307ba2babc034cbc66a893d4a31d5f4b
3
  size 9962580296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf5e12b0baf0f9d2c8ffe822fbfba513d3ba03f3436221f8ec810bba716cea52
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:bc32d7ec503691ed1fd94f228ffae10b0300c79b07db7c89cbb38cee715a67c4
3
  size 9949328904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44d90f1586bbb63040cccf8a015246cc3ec0788a4b172d46a12496dffea7d9bc
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 sha256:9d4f0b20527b459377d6ccd447e1b45065724b44a66b40187b4603a8b4d42798
3
  size 3870584832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a0903c3b729659c02b176608f64f071c83504a8f6b6dbab391bb73f3b42886a
3
  size 3870584832