kerk86 commited on
Commit
6508194
·
verified ·
1 Parent(s): 92e9ce3

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. README.md +46 -0
  2. config.yaml +3 -3
  3. lora.safetensors +2 -2
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: flux-1-dev-non-commercial-license
4
+ license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
5
+ language:
6
+ - en
7
+ tags:
8
+ - flux
9
+ - diffusers
10
+ - lora
11
+ - replicate
12
+ base_model: "black-forest-labs/FLUX.1-dev"
13
+ pipeline_tag: text-to-image
14
+ # widget:
15
+ # - text: >-
16
+ # prompt
17
+ # output:
18
+ # url: https://...
19
+ instance_prompt: BevzyukN
20
+ ---
21
+
22
+ # Lora_Beast
23
+
24
+ <Gallery />
25
+
26
+ Trained on Replicate using:
27
+
28
+ https://replicate.com/ostris/flux-dev-lora-trainer/train
29
+
30
+
31
+ ## Trigger words
32
+ You should use `BevzyukN` to trigger the image generation.
33
+
34
+
35
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
36
+
37
+ ```py
38
+ from diffusers import AutoPipelineForText2Image
39
+ import torch
40
+
41
+ pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
42
+ pipeline.load_lora_weights('kerk86/Lora_beast', weight_name='lora.safetensors')
43
+ image = pipeline('your prompt').images[0]
44
+ ```
45
+
46
+ For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
config.yaml CHANGED
@@ -12,7 +12,7 @@ config:
12
  linear_alpha: 32
13
  save:
14
  dtype: float16
15
- save_every: 1201
16
  max_step_saves_to_keep: 1
17
  datasets:
18
  - folder_path: input_images
@@ -27,7 +27,7 @@ config:
27
  - 1024
28
  train:
29
  batch_size: 1
30
- steps: 1200
31
  gradient_accumulation_steps: 1
32
  train_unet: true
33
  train_text_encoder: false
@@ -46,7 +46,7 @@ config:
46
  quantize: true
47
  sample:
48
  sampler: flowmatch
49
- sample_every: 1201
50
  width: 1024
51
  height: 1024
52
  prompts: []
 
12
  linear_alpha: 32
13
  save:
14
  dtype: float16
15
+ save_every: 1001
16
  max_step_saves_to_keep: 1
17
  datasets:
18
  - folder_path: input_images
 
27
  - 1024
28
  train:
29
  batch_size: 1
30
+ steps: 1000
31
  gradient_accumulation_steps: 1
32
  train_unet: true
33
  train_text_encoder: false
 
46
  quantize: true
47
  sample:
48
  sampler: flowmatch
49
+ sample_every: 1001
50
  width: 1024
51
  height: 1024
52
  prompts: []
lora.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf224265bcfbfefff651c0980dc3881e4e340f73b8625c9b4d189d526e1279d1
3
- size 171969424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ef3b923363acb2b64e74234444e65ea8eba1adaf25fcf56262e62dbd9b47770
3
+ size 343805464