Upload folder using huggingface_hub
Browse files- README.md +21 -48
- config.yaml +60 -0
- lora.safetensors +3 -0
README.md
CHANGED
@@ -1,73 +1,46 @@
|
|
1 |
---
|
2 |
license: other
|
3 |
-
|
|
|
|
|
|
|
4 |
tags:
|
5 |
-
-
|
6 |
-
- diffusers-training
|
7 |
- diffusers
|
8 |
- lora
|
9 |
- replicate
|
10 |
-
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
|
|
|
|
16 |
---
|
17 |
|
18 |
-
|
19 |
-
should probably proofread and complete it, then remove this comment. -->
|
20 |
-
|
21 |
-
|
22 |
-
# Flux DreamBooth LoRA - lumin8/jtrudeau
|
23 |
|
24 |
<Gallery />
|
25 |
|
26 |
-
|
27 |
-
|
28 |
-
These are lumin8/jtrudeau DreamBooth LoRA weights for FLUX.1-dev.
|
29 |
|
30 |
-
|
31 |
|
32 |
-
Was LoRA for the text encoder enabled? False.
|
33 |
|
34 |
## Trigger words
|
|
|
35 |
|
36 |
-
You should use `a photo of JTrudeau` to trigger the image generation.
|
37 |
-
|
38 |
-
## Download model
|
39 |
-
|
40 |
-
[Download the *.safetensors LoRA](lumin8/jtrudeau/tree/main) in the Files & versions tab.
|
41 |
|
42 |
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
|
43 |
|
44 |
```py
|
45 |
from diffusers import AutoPipelineForText2Image
|
46 |
import torch
|
47 |
-
pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to('cuda')
|
48 |
-
pipeline.load_lora_weights('lumin8/jtrudeau', weight_name='pytorch_lora_weights.safetensors')
|
49 |
-
image = pipeline('a photo of JTrudeau').images[0]
|
50 |
-
```
|
51 |
-
|
52 |
-
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)
|
53 |
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
## Intended uses & limitations
|
60 |
-
|
61 |
-
#### How to use
|
62 |
-
|
63 |
-
```python
|
64 |
-
# TODO: add an example code snippet for running this diffusion pipeline
|
65 |
```
|
66 |
|
67 |
-
|
68 |
-
|
69 |
-
[TODO: provide examples of latent issues and potential remediations]
|
70 |
-
|
71 |
-
## Training details
|
72 |
-
|
73 |
-
[TODO: describe the data used to train the model]
|
|
|
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: jtrudeau
|
20 |
---
|
21 |
|
22 |
+
# Jtrudeau
|
|
|
|
|
|
|
|
|
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 `jtrudeau` 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('lumin8/jtrudeau', 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
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
job: custom_job
|
2 |
+
config:
|
3 |
+
name: flux_train_replicate
|
4 |
+
process:
|
5 |
+
- type: custom_sd_trainer
|
6 |
+
training_folder: output
|
7 |
+
device: cuda:0
|
8 |
+
trigger_word: jtrudeau
|
9 |
+
network:
|
10 |
+
type: lora
|
11 |
+
linear: 50
|
12 |
+
linear_alpha: 50
|
13 |
+
save:
|
14 |
+
dtype: float16
|
15 |
+
save_every: 2001
|
16 |
+
max_step_saves_to_keep: 1
|
17 |
+
datasets:
|
18 |
+
- folder_path: input_images
|
19 |
+
caption_ext: txt
|
20 |
+
caption_dropout_rate: 0.05
|
21 |
+
shuffle_tokens: false
|
22 |
+
cache_latents_to_disk: false
|
23 |
+
cache_latents: true
|
24 |
+
resolution:
|
25 |
+
- 512
|
26 |
+
- 768
|
27 |
+
- 1024
|
28 |
+
train:
|
29 |
+
batch_size: 1
|
30 |
+
steps: 2000
|
31 |
+
gradient_accumulation_steps: 1
|
32 |
+
train_unet: true
|
33 |
+
train_text_encoder: false
|
34 |
+
content_or_style: balanced
|
35 |
+
gradient_checkpointing: true
|
36 |
+
noise_scheduler: flowmatch
|
37 |
+
optimizer: adamw8bit
|
38 |
+
lr: 0.0004
|
39 |
+
ema_config:
|
40 |
+
use_ema: true
|
41 |
+
ema_decay: 0.99
|
42 |
+
dtype: bf16
|
43 |
+
model:
|
44 |
+
name_or_path: FLUX.1-dev
|
45 |
+
is_flux: true
|
46 |
+
quantize: true
|
47 |
+
sample:
|
48 |
+
sampler: flowmatch
|
49 |
+
sample_every: 2001
|
50 |
+
width: 1024
|
51 |
+
height: 1024
|
52 |
+
prompts: []
|
53 |
+
neg: ''
|
54 |
+
seed: 42
|
55 |
+
walk_seed: true
|
56 |
+
guidance_scale: 3.5
|
57 |
+
sample_steps: 28
|
58 |
+
meta:
|
59 |
+
name: flux_train_replicate
|
60 |
+
version: '1.0'
|
lora.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0eb067b58c7aed8cd836c3c1495ccfc8464ed07f26ffd19d6bfb65cddf0e3971
|
3 |
+
size 537120512
|