Text-to-Image
Diffusers
template:sd-lora
flux
lora
GliffyTrainer commited on
Commit
0f05e6d
·
verified ·
1 Parent(s): 6561b10

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - diffusers
4
+ - text-to-image
5
+ - template:sd-lora
6
+ - base_model:black-forest-labs/FLUX.1-dev
7
+ - base_model:finetune:black-forest-labs/FLUX.1-dev
8
+ - license:other
9
+ - region:us
10
+ - flux
11
+ - lora
12
+ widget:
13
+ - output:
14
+ url: samples/1750983109363__000002000_0.jpg
15
+ text: b0rg woman
16
+ - output:
17
+ url: samples/1750983134227__000002000_1.jpg
18
+ text: b0rg man
19
+ - output:
20
+ url: samples/1750983159054__000002000_2.jpg
21
+ text: b0rg man in charging station
22
+ - output:
23
+ url: samples/1750983183882__000002000_3.jpg
24
+ text: b0rg woman in charging station
25
+ base_model: black-forest-labs/FLUX.1-dev
26
+ trigger: "b0rg"
27
+ instance_prompt: "b0rg"
28
+ license: other
29
+ license_name: flux-1-dev-non-commercial-license
30
+ license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
31
+ ---
32
+ # b0rg
33
+ Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `Angelo-ec24`.
34
+ <Gallery />
35
+ ## Trigger words
36
+ You should use `b0rg` to trigger the image generation.
37
+ ## Download model
38
+ Weights for this model are available in Safetensors format.
39
+ [Download](/glif-loradex-trainer/Angelo-ec24_b0rg/tree/main) them in the Files & versions tab.
40
+
41
+ ## License
42
+ This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
43
+
b0rg.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa1d7cdc051469e00f30dd53df6bad715a75c79889e11bc8d8df08dfb3922f91
3
+ size 451202688
config.yaml ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ config:
2
+ name: b0rg
3
+ process:
4
+ - datasets:
5
+ - cache_latents_to_disk: true
6
+ caption_dropout_rate: 0.2
7
+ caption_ext: txt
8
+ folder_path: /root/lorahub/flux-dev/b0rg/dataset
9
+ resolution:
10
+ - 512
11
+ - 768
12
+ - 1024
13
+ shuffle_tokens: false
14
+ token_dropout_rate: 0.01
15
+ device: cuda:0
16
+ model:
17
+ is_flux: true
18
+ name_or_path: black-forest-labs/FLUX.1-dev
19
+ quantize: true
20
+ text_encoder_bits: 8
21
+ network:
22
+ linear: 42
23
+ linear_alpha: 42
24
+ transformer_only: true
25
+ type: lora
26
+ performance_log_every: 500
27
+ sample:
28
+ guidance_scale: 3.5
29
+ height: 1024
30
+ neg: ''
31
+ prompts:
32
+ - '[trigger] woman'
33
+ - '[trigger] man'
34
+ - '[trigger] man in charging station'
35
+ - '[trigger] woman in charging station'
36
+ sample_every: 500
37
+ sample_steps: 25
38
+ sampler: flowmatch
39
+ seed: 42
40
+ walk_seed: true
41
+ width: 1024
42
+ save:
43
+ dtype: float16
44
+ max_step_saves_to_keep: 3
45
+ save_every: 500
46
+ save_format: diffusers
47
+ train:
48
+ batch_size: 1
49
+ dtype: bf16
50
+ ema_config:
51
+ ema_decay: 0.99
52
+ use_ema: true
53
+ gradient_accumulation_steps: 1
54
+ gradient_checkpointing: true
55
+ linear_timesteps: true
56
+ loss_type: mse
57
+ lr: 0.0003
58
+ noise_scheduler: flowmatch
59
+ optimizer: adamw8bit
60
+ reg_weight: 1
61
+ steps: 2000
62
+ target_noise_multiplier: 1
63
+ train_text_encoder: false
64
+ train_unet: true
65
+ training_folder: /root/lorahub/flux-dev
66
+ trigger_word: b0rg
67
+ type: loradex_trainer
68
+ job: extension
69
+ meta:
70
+ description: ''
samples/1750983109363__000002000_0.jpg ADDED
samples/1750983134227__000002000_1.jpg ADDED
samples/1750983159054__000002000_2.jpg ADDED
samples/1750983183882__000002000_3.jpg ADDED