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 2023-11-03 05:39:46 +00:00 committed by huggingface-web
parent 94720b9ba1
commit bd9d13c7b4
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
README.md
View File

@ -150,7 +150,7 @@ 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: 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):**
```bash ```bash
export MODEL_NAME="segmind/SSD-1B" export MODEL_NAME="segmind/SSD-1B"
export VAE_NAME="madebyollin/sdxl-vae-fp16-fix" export VAE_NAME="madebyollin/sdxl-vae-fp16-fix"
@ -166,11 +166,12 @@ accelerate launch train_text_to_image_lora_sdxl.py \
--learning_rate=1e-04 --lr_scheduler="constant" --lr_warmup_steps=0 \ --learning_rate=1e-04 --lr_scheduler="constant" --lr_warmup_steps=0 \
--mixed_precision="fp16" \ --mixed_precision="fp16" \
--seed=42 \ --seed=42 \
--output_dir="sd-pokemon-model-lora-sdxl" \ --output_dir="sd-pokemon-model-lora-ssd" \
--validation_prompt="cute dragon creature" --report_to="wandb" \ --validation_prompt="cute dragon creature" --report_to="wandb" \
--push_to_hub --push_to_hub
``` ```
- **[LoRA](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_lora_sdxl.py):**
- **[Fine-Tune](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_sdxl.py):**
```bash ```bash
export MODEL_NAME="segmind/SSD-1B" export MODEL_NAME="segmind/SSD-1B"
export VAE_NAME="madebyollin/sdxl-vae-fp16-fix" export VAE_NAME="madebyollin/sdxl-vae-fp16-fix"
@ -192,7 +193,7 @@ accelerate launch train_text_to_image_sdxl.py \
--report_to="wandb" \ --report_to="wandb" \
--validation_prompt="a cute Sundar Pichai creature" --validation_epochs 5 \ --validation_prompt="a cute Sundar Pichai creature" --validation_epochs 5 \
--checkpointing_steps=5000 \ --checkpointing_steps=5000 \
--output_dir="sdxl-pokemon-model" \ --output_dir="ssd-pokemon-model" \
--push_to_hub --push_to_hub
``` ```
- **[Dreambooth LoRA](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_lora_sdxl.py):** - **[Dreambooth LoRA](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_lora_sdxl.py):**