pull

README.md

@@ -16,15 +16,11 @@ library_name: diffusers
 
 # Segmind Stable Diffusion 1B (SSD-1B) Model Card
 
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/62039c2d91d53938a643317d/WveKcu7q5PyZEwNezyyMC.png)
-
-## 📣 Read our [technical report](https://huggingface.co/papers/2401.02677) for more details on our disillation method
-
-## AUTOMATIC1111 compatibility added. Supporting file [here](https://huggingface.co/segmind/SSD-1B/blob/main/SSD-1B-A1111.safetensors)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/62039c2d91d53938a643317d/0Iu_0f0d1ihGy0YiOd9uS.png)
 
 ## Demo
 
-Try out the model at [Segmind SSD-1B](https://www.segmind.com/models/ssd-1b?utm_source=hf) for ⚡ fastest inference. You can also try it on [🤗 Spaces](https://huggingface.co/spaces/segmind/Segmind-Stable-Diffusion)
+Try out the model at [Segmind SSD-1B](https://www.segmind.com/models/ssd-1b) for ⚡ fastest inference. You can also try it on [🤗 Spaces](https://huggingface.co/spaces/segmind/Segmind-Stable-Diffusion)
 
 ## Model Description
 
@@ -154,7 +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:
 
-- **[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
 export MODEL_NAME="segmind/SSD-1B"
 export VAE_NAME="madebyollin/sdxl-vae-fp16-fix"
@@ -170,12 +166,11 @@ accelerate launch train_text_to_image_lora_sdxl.py \
   --learning_rate=1e-04 --lr_scheduler="constant" --lr_warmup_steps=0 \
   --mixed_precision="fp16" \
   --seed=42 \
-  --output_dir="sd-pokemon-model-lora-ssd" \
+  --output_dir="sd-pokemon-model-lora-sdxl" \
   --validation_prompt="cute dragon creature" --report_to="wandb" \
   --push_to_hub
 ```
-
-- **[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
 export MODEL_NAME="segmind/SSD-1B"
 export VAE_NAME="madebyollin/sdxl-vae-fp16-fix"
@@ -197,7 +192,7 @@ accelerate launch train_text_to_image_sdxl.py \
   --report_to="wandb" \
   --validation_prompt="a cute Sundar Pichai creature" --validation_epochs 5 \
   --checkpointing_steps=5000 \
-  --output_dir="ssd-pokemon-model" \
+  --output_dir="sdxl-pokemon-model" \
   --push_to_hub
 ```
 - **[Dreambooth LoRA](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_lora_sdxl.py):**
@@ -235,16 +230,4 @@ The SSD-1B Model is not suitable for creating factual or accurate representation
 ## Limitations and Bias
 
 Limitations & Bias
-The SSD-1B Model has some challenges in embodying absolute photorealism, especially in human depictions. While it grapples with incorporating clear text and maintaining the fidelity of complex compositions due to its autoencoding approach, these hurdles pave the way for future enhancements. Importantly, the model's exposure to a diverse dataset, though not a panacea for ingrained societal and digital biases, represents a foundational step towards more equitable technology. Users are encouraged to interact with this pioneering tool with an understanding of its current limitations, fostering an environment of conscious engagement and anticipation for its continued evolution.
-
-## Citation
-```
-@misc{gupta2024progressive,
-      title={Progressive Knowledge Distillation Of Stable Diffusion XL Using Layer Level Loss}, 
-      author={Yatharth Gupta and Vishnu V. Jaddipal and Harish Prabhala and Sayak Paul and Patrick Von Platen},
-      year={2024},
-      eprint={2401.02677},
-      archivePrefix={arXiv},
-      primaryClass={cs.CV}
-}
-```
+The SSD-1B Model has some challenges in embodying absolute photorealism, especially in human depictions. While it grapples with incorporating clear text and maintaining the fidelity of complex compositions due to its autoencoding approach, these hurdles pave the way for future enhancements. Importantly, the model's exposure to a diverse dataset, though not a panacea for ingrained societal and digital biases, represents a foundational step towards more equitable technology. Users are encouraged to interact with this pioneering tool with an understanding of its current limitations, fostering an environment of conscious engagement and anticipation for its continued evolution.

SSD-1B-A1111.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1895a00bfc769a00b0c0c43a95e433e79e9db8a85402b45a33e8448785bde94d
-size 4465671322