Upload folder using huggingface_hub

README.md

@@ -0,0 +1,31 @@
+---
+tags:
+- text-to-image
+- flux
+- lora
+- diffusers
+- template:sd-lora
+- fluxgym
+
+
+base_model: black-forest-labs/FLUX.1-dev
+instance_prompt: xsrithika
+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
+---
+
+# srithika
+
+A Flux LoRA trained on a local computer with [Fluxgym](https://github.com/cocktailpeanut/fluxgym)
+
+<Gallery />
+
+## Trigger words
+
+You should use `xsrithika` 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.
+

sample_prompts.txt

@@ -1 +1 @@
-xsrithika a woman in a maroon and orange sari standing in front of a gate with trees in the background. She is identified as Nayanthara, and the image is in high definition with a resolution of 1080p and 4k
+xsrithika a woman with long black hair and a green sari smiling at the camera against a white and brown 

srithika.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5cbed64dcdff81d084d99fe8d70cb635c52a26009639242684070bac6d72016
+size 39762152

train.sh

@@ -16,13 +16,13 @@ accelerate launch \
   --save_precision bf16 \
   --network_module networks.lora_flux \
   --network_dim 4 \
-  --optimizer_type adamw8bit \--sample_prompts="/teamspace/studios/this_studio/fluxgym/outputs/srithika/sample_prompts.txt" --sample_every_n_steps="1" \
+  --optimizer_type adamw8bit \
   --learning_rate 8e-4 \
   --cache_text_encoder_outputs \
   --cache_text_encoder_outputs_to_disk \
   --fp8_base \
   --highvram \
-  --max_train_epochs 5 \
+  --max_train_epochs 2 \
   --save_every_n_epochs 4 \
   --dataset_config "/teamspace/studios/this_studio/fluxgym/outputs/srithika/dataset.toml" \
   --output_dir "/teamspace/studios/this_studio/fluxgym/outputs/srithika" \