rvorias commited on
Commit
3cfb77a
1 Parent(s): 4609659

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/1730144840164__000001500_0.jpg
15
+ text: sloth driving a car, flshtt
16
+ - output:
17
+ url: samples/1730144864716__000001500_1.jpg
18
+ text: cyborg samurai flshtt
19
+ - output:
20
+ url: samples/1730144889260__000001500_2.jpg
21
+ text: a bird catching a worm, flshtt
22
+ base_model: black-forest-labs/FLUX.1-dev
23
+ trigger: flshtt
24
+ instance_prompt: flshtt
25
+ license: other
26
+ license_name: flux-1-dev-non-commercial-license
27
+ license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
28
+ ---
29
+ # appelsiensam_flashtattoo
30
+ 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 `i12bp8`.
31
+ <Gallery />
32
+ ## Trigger words
33
+ You should use `flshtt` to trigger the image generation.
34
+ ## Download model
35
+ Weights for this model are available in Safetensors format.
36
+ [Download](/glif-loradex-trainer/i12bp8_appelsiensam_flashtattoo/tree/main) them in the Files & versions tab.
37
+
38
+ ## License
39
+ 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).
40
+
appelsiensam_flashtattoo.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbb3ff8b6a2fac07916f795337a820a46c9c329a863053d151831d248af86b1c
3
+ size 451202840
appelsiensam_flashtattoo_000000500.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9caac0b216f4ab2b9033b2f1c64e72310191de6717ac08f64a722c59b53d2587
3
+ size 451202832
appelsiensam_flashtattoo_000001000.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:067c0971914a773df5d39d40fefe3a559cf64967315c5d61af87777d997f401c
3
+ size 451202840
config.yaml ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ config:
2
+ name: appelsiensam_flashtattoo
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/appelsiensam_flashtattoo/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
+ height: 1024
29
+ neg: ''
30
+ prompts:
31
+ - sloth driving a car, [trigger]
32
+ - cyborg samurai [trigger]
33
+ - a bird catching a worm, [trigger]
34
+ sample_every: 500
35
+ sample_steps: 25
36
+ sampler: flowmatch
37
+ seed: 941391
38
+ walk_seed: true
39
+ width: 1024
40
+ save:
41
+ dtype: float16
42
+ max_step_saves_to_keep: 3
43
+ save_every: 500
44
+ save_format: diffusers
45
+ train:
46
+ batch_size: 1
47
+ dtype: bf16
48
+ ema_config:
49
+ ema_decay: 0.99
50
+ use_ema: true
51
+ gradient_accumulation_steps: 1
52
+ gradient_checkpointing: true
53
+ linear_timesteps: true
54
+ loss_type: mse
55
+ lr: 0.0002
56
+ noise_scheduler: flowmatch
57
+ optimizer: adamw8bit
58
+ reg_weight: 1
59
+ steps: 1500
60
+ target_noise_multiplier: 1
61
+ train_text_encoder: false
62
+ train_unet: true
63
+ training_folder: /root/lorahub
64
+ trigger_word: flshtt
65
+ type: sd_trainer
66
+ job: extension
67
+ meta:
68
+ description: A specialized LoRA for generating traditional American flash tattoo
69
+ art featuring bold black outlines, simple clean linework
samples/1730142124196__000000000_0.jpg ADDED
samples/1730142148732__000000000_1.jpg ADDED
samples/1730142173270__000000000_2.jpg ADDED
samples/1730143031323__000000500_0.jpg ADDED
samples/1730143055992__000000500_1.jpg ADDED
samples/1730143080738__000000500_2.jpg ADDED
samples/1730143943289__000001000_0.jpg ADDED
samples/1730143968208__000001000_1.jpg ADDED
samples/1730143992763__000001000_2.jpg ADDED
samples/1730144840164__000001500_0.jpg ADDED
samples/1730144864716__000001500_1.jpg ADDED
samples/1730144889260__000001500_2.jpg ADDED