Update README.md

README.md

@@ -42,17 +42,30 @@ widget:
 # OpenDalle
 
 <Gallery />
-NOTE: This is outdated! newest version 1.1 can be found here!  https://huggingface.co/dataautogpt3/OpenDalleV1.1
+## NOTE: This is outdated! newest version 1.1 can be found here!  https://huggingface.co/dataautogpt3/OpenDalleV1.1
 
 
 I'm thrilled to share an update on a recent project of mine. After some dedicated work, I've developed a highly effective text-to-image model. This innovation results from integrating the DPO model from Hugging Face with several advanced counterparts, including Juggernaut7XL, ALBEDOXL, MEARGEHEAVEN, and a model of my own design. The outcome is a unique fusion that showcases exceptional prompt adherence and semantic understanding, it seems to be a step above base SDXL and a step closer to DALLE-3 in terms of prompt comprehension. Notably, this model excels in interpreting and adhering to the given prompts, focusing more on semantic accuracy than on ultra-high-fidelity image generation.
 also available on ```https://civitai.com/models/238116/opendalle ```
 
-V1.1 has been released please see the note at the top of this repo or click on my profile! 
+## Settings for OpenDalle v1.0
+
+Use these settings for the best results with OpenDalle v1.0:
+
+CFG Scale: Use a CFG scale of 8 to 7
+
+Steps: 60 to 70 steps for more detail, 35 steps for faster results.
+
+Sampler: DPM2
+
+Scheduler: Normal or Karras
+
+Negative Prompts: Avoid using negative prompts for better-quality images.
 
 ## `*.safetensors` for AUTOMATIC1111, ComfyUI, InvokeAI
 [Download *.safetensors file](https://huggingface.co/dataautogpt3/OpenDalle/resolve/main/OpenDalle.safetensors?download=true)
 
+
 ## Use it with 🧨 diffusers
 ```python
 from diffusers import AutoPipelineForText2Image