Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,24 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_000144_00_20250202171752.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_000288_00_20250202172504.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_000432_00_20250202173214.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_000576_00_20250202173925.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_000720_00_20250202174635.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_000864_00_20250202175346.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_001008_00_20250202180056.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_001152_00_20250202180806.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_001296_00_20250202181517.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_001440_00_20250202182227.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_001584_00_20250202182937.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_001728_00_20250202183647.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_001872_00_20250202184357.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_002016_00_20250202185107.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_002160_00_20250202185817.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_002304_00_20250202190528.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_002448_00_20250202191239.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_002592_00_20250202191949.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_002736_00_20250202192659.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_002880_00_20250202193409.png filter=lfs diff=lfs merge=lfs -text
+sample/voicemod-key-lora_003024_00_20250202194120.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,33 @@
+---
+tags:
+- text-to-image
+- flux
+- lora
+- diffusers
+- template:sd-lora
+- fluxgym
+widget:
+-   output:
+        url: sample/voicemod-key-lora_003024_00_20250202194120.png
+    text: v01c3m0dk3y
+base_model: black-forest-labs/FLUX.1-dev
+instance_prompt: v01c3m0dk3y
+license: other
+license_name: flux-1-dev-non-commercial-license
+license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
+---
+
+# voicemod-key-lora
+
+A Flux LoRA trained on a local computer with [Fluxgym](https://github.com/cocktailpeanut/fluxgym)
+
+<Gallery />
+
+## Trigger words
+
+You should use `v01c3m0dk3y` to trigger the image generation.
+
+## Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, Forge, etc.
+
+Weights for this model are available in Safetensors format.
+

dataset.toml

@@ -0,0 +1,14 @@
+[general]
+shuffle_caption = false
+caption_extension = '.txt'
+keep_tokens = 1
+
+[[datasets]]
+resolution = 1024
+batch_size = 1
+keep_tokens = 1
+
+  [[datasets.subsets]]
+  image_dir = '/workspace/fluxgym/datasets/voicemod-key-lora'
+  class_tokens = 'v01c3m0dk3y'
+  num_repeats = 10

sample_prompts.txt

@@ -0,0 +1 @@
+v01c3m0dk3y

train.sh

@@ -0,0 +1,34 @@
+accelerate launch \
+  --mixed_precision bf16 \
+  --num_cpu_threads_per_process 1 \
+  sd-scripts/flux_train_network.py \
+  --pretrained_model_name_or_path "/workspace/fluxgym/models/unet/flux1-dev.sft" \
+  --clip_l "/workspace/fluxgym/models/clip/clip_l.safetensors" \
+  --t5xxl "/workspace/fluxgym/models/clip/t5xxl_fp16.safetensors" \
+  --ae "/workspace/fluxgym/models/vae/ae.sft" \
+  --cache_latents_to_disk \
+  --save_model_as safetensors \
+  --sdpa --persistent_data_loader_workers \
+  --max_data_loader_n_workers 2 \
+  --seed 42 \
+  --gradient_checkpointing \
+  --mixed_precision bf16 \
+  --save_precision bf16 \
+  --network_module networks.lora_flux \
+  --network_dim 4 \
+  --optimizer_type adamw8bit \--sample_prompts="/workspace/fluxgym/outputs/voicemod-key-lora/sample_prompts.txt" --sample_every_n_steps="144" \
+  --learning_rate 8e-4 \
+  --cache_text_encoder_outputs \
+  --cache_text_encoder_outputs_to_disk \
+  --fp8_base \
+  --highvram \
+  --max_train_epochs 16 \
+  --save_every_n_epochs 4 \
+  --dataset_config "/workspace/fluxgym/outputs/voicemod-key-lora/dataset.toml" \
+  --output_dir "/workspace/fluxgym/outputs/voicemod-key-lora" \
+  --output_name voicemod-key-lora \
+  --timestep_sampling shift \
+  --discrete_flow_shift 3.1582 \
+  --model_prediction_type raw \
+  --guidance_scale 1 \
+  --loss_type l2 \

voicemod-key-lora-000004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d5924a71058939d8e8a00818f1e377e2e736aee476761a8f85038559b64883a
+size 39757408

voicemod-key-lora-000008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5239e5cc5bc20d1871e4f0eed144361f0e1225622d73731d51117a426c1b7af8
+size 39757416

voicemod-key-lora-000012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51474b8c8c04b25df8bfde19f0f0cee38b55c335f04956fa7b9018da6dbc7b1c
+size 39757416

voicemod-key-lora.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:796a25d8e39d74da4c25c52b5d70b0e033cd15041eb86e0f4e2a16949faa7b71
+size 39757408