razzz
This model has a creepy bias producing great horror picture with great fidelity.
You don't need any specific trigger words. Any horror related prompt will result in a strong level of creep.
Based on SD1.5
Please use vae-ft-mse-840000-ema-recommended VAE for optimal results
I found that DPM2 a Karras or Euler A- 40 Steps - CFG Scale 7 is a great sweet spot
Prompt Examples:
Prompt: a horror beyond my comprehension staring at me, with massive, terrifying eyes and a crazed smile. infamous dark photograph, in a dark alley, strong film grain, sharp tooth, inside a liminal space of nightmares
Negative prompt: 3D, cartoon
Steps: 40, Sampler: Euler a, CFG scale: 7, Seed: 3347322281, Size: 768x768,
Prompt: realistic detailed image of a little girl looking under the bed in a girlish room. a demon-monster is hiding under the bed in the shadow. by Ayami Kojima, Amano, Karol Bak, Greg Hildebrandt, and Mark Brooks, Neo-Gothic, gothic, rich deep colors. Beksinski painting, part by Adrian Ghenie and Gerhard Richter. art by Takato Yamamoto. masterpiece
Steps: 40, Sampler: DPM2 a Karras, CFG scale: 7, Seed: 615468215, Size: 640x640,
Prompt: a toxic ooze creature in a pixar artstyle, adorable and whimsical,, fantasy, elegant, digital painting, artstation, unreal engine, octane render, concept art, matte, sharp focus, vibrant colors, high contrast, illustration, art by james jean and philippe druillet and justin gerard
Steps: 40, Sampler: DPM2 a Karras, CFG scale: 7, Seed: 2205359249, Size: 640x640
Prompt: faded closeup flash photography of a crazy creepy bleeding woman wearing dirty old rags in a doorway
Negative prompt: makeup, nude, high contrast, vignette, mask, drawing, hdr
Steps: 40, Sampler: DPM2 a Karras, CFG scale: 7, Seed: 720264529, Size: 768x768
The model is working great from 512x512 through 768x768.
Hugging Face Link
What is Creepy Diffusion?
Creepy Diffusion is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user razzz. Derived from the powerful Stable Diffusion (SD 1.5) model, Creepy Diffusion has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that Creepy Diffusion is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as horror, creepy.
With a rating of 4.17 and over 12 ratings, Creepy Diffusion is a popular choice among users for generating high-quality images from text prompts.
Can I download Creepy Diffusion?
Yes! You can download the latest version of Creepy Diffusion from here.
How to use Creepy Diffusion?
To use Creepy Diffusion, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like Creepy Diffusion, check out our crash course in AI image generation.
Popularity
Info
Version V1.0: 1 File
About this version: V1.0
Initial Release
2 Versions
Go ahead and upload yours!
