segmind/SSD-1B
segmind/SSD-1B
1
0
Overview Code Discussions Pull Requests Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Yatharth Gupta 2023-10-24 06:36:34 +00:00 committed by huggingface-web
parent ca0b3b0b28
commit 4d09c9a47c
1 changed files with 72 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

75
README.md
View File

@ -133,9 +133,78 @@ The Segmind Stable Diffusion Model is suitable for research and practical applic
The Segmind Stable Diffusion Model can also be used directly with the 🧨 Diffusers library training scripts for further training, including:
- **[Fine-Tune](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_sdxl.py)**
- **[LoRA](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_lora_sdxl.py)**
- **[Dreambooth LoRA](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_lora_sdxl.py)**
- **[Fine-Tune](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_sdxl.py):**
```bash
export MODEL_NAME="segmind/SSD-1B"
export VAE_NAME="madebyollin/sdxl-vae-fp16-fix"
export DATASET_NAME="lambdalabs/pokemon-blip-captions"
accelerate launch train_text_to_image_lora_sdxl.py \
--pretrained_model_name_or_path=$MODEL_NAME \
--pretrained_vae_model_name_or_path=$VAE_NAME \
--dataset_name=$DATASET_NAME --caption_column="text" \
--resolution=1024 --random_flip \
--train_batch_size=1 \
--num_train_epochs=2 --checkpointing_steps=500 \
--learning_rate=1e-04 --lr_scheduler="constant" --lr_warmup_steps=0 \
--mixed_precision="fp16" \
--seed=42 \
--output_dir="sd-pokemon-model-lora-sdxl" \
--validation_prompt="cute dragon creature" --report_to="wandb" \
--push_to_hub
```
- **[LoRA](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_lora_sdxl.py):**
```bash
export MODEL_NAME="segmind/SSD-1B"
export VAE_NAME="madebyollin/sdxl-vae-fp16-fix"
export DATASET_NAME="lambdalabs/pokemon-blip-captions"
accelerate launch train_text_to_image_sdxl.py \
--pretrained_model_name_or_path=$MODEL_NAME \
--pretrained_vae_model_name_or_path=$VAE_NAME \
--dataset_name=$DATASET_NAME \
--enable_xformers_memory_efficient_attention \
--resolution=512 --center_crop --random_flip \
--proportion_empty_prompts=0.2 \
--train_batch_size=1 \
--gradient_accumulation_steps=4 --gradient_checkpointing \
--max_train_steps=10000 \
--use_8bit_adam \
--learning_rate=1e-06 --lr_scheduler="constant" --lr_warmup_steps=0 \
--mixed_precision="fp16" \
--report_to="wandb" \
--validation_prompt="a cute Sundar Pichai creature" --validation_epochs 5 \
--checkpointing_steps=5000 \
--output_dir="sdxl-pokemon-model" \
--push_to_hub
```
- **[Dreambooth LoRA](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_lora_sdxl.py):**
```bash
export MODEL_NAME="segmind/SSD-1B"
export INSTANCE_DIR="dog"
export OUTPUT_DIR="lora-trained-xl"
export VAE_PATH="madebyollin/sdxl-vae-fp16-fix"
accelerate launch train_dreambooth_lora_sdxl.py \
--pretrained_model_name_or_path=$MODEL_NAME \
--instance_data_dir=$INSTANCE_DIR \
--pretrained_vae_model_name_or_path=$VAE_PATH \
--output_dir=$OUTPUT_DIR \
--mixed_precision="fp16" \
--instance_prompt="a photo of sks dog" \
--resolution=1024 \
--train_batch_size=1 \
--gradient_accumulation_steps=4 \
--learning_rate=1e-5 \
--report_to="wandb" \
--lr_scheduler="constant" \
--lr_warmup_steps=0 \
--max_train_steps=500 \
--validation_prompt="A photo of sks dog in a bucket" \
--validation_epochs=25 \
--seed="0" \
--push_to_hub
```
### Out-of-Scope Use