README.md

---
license: creativeml-openrail-m
---
**Archer Diffusion**

This is the fine-tuned Stable Diffusion model trained on screenshots from the TV-show Archer.
Use the tokens **_archer style_** in your prompts for the effect.

If you enjoy this model, please check out my other models on [Huggingface](https://huggingface.co/nitrosocke)

**Portraits rendered with the model:**
![Portrait Samples](https://huggingface.co/nitrosocke/archer-diffusion/resolve/main/archer-diffusion-samples.png)
**Celebrities rendered with the model:**
![Celebrities Samples](https://huggingface.co/nitrosocke/archer-diffusion/resolve/main/archer-diffusion-samples4s.png)
**Landscapes rendered with the model:**
![Landscape Samples](https://huggingface.co/nitrosocke/archer-diffusion/resolve/main/archer-diffusion-samples3.png)
**Animals rendered with the model:**
![Animal Samples](https://huggingface.co/nitrosocke/archer-diffusion/resolve/main/archer-diffusion-samples2.png)
**Sample images used for training:**
![Training Samples](https://huggingface.co/nitrosocke/archer-diffusion/resolve/main/archer-diffusion-dataset.png)

#### Prompt and settings for portraits:
**archer style beautiful portrait of ariana grande**
_Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 946707299, Size: 512x704_
#### Prompt and settings for landscapes:
**archer style suburban street night blue indoor lighting Negative prompt: grey cars**
_Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 2915669764, Size: 1024x576_

This model was trained using the diffusers based dreambooth training and prior-preservation loss in 4.000 steps and using the _train-text-encoder_ feature.