Stable Diffusion

Informations

• Module : Stable diffusion

• Function : Generate images from a prompt and a negative prompt using Stable Diffusion

• Input(s) : Prompt, negative prompt

• Output(s) : Image(s)

• HF model page :

  • SG161222/Realistic_Vision_V3.0_VAE
  • IDKiro/sdxs-512-dreamshaper
  • IDKiro/sdxs-512-0.9
  • RunDiffusion/Juggernaut-XL-Lightning
  • Fluently-XL-v3-Lightning,
  • fluently/Fluently-XL-v4
  • recoilme/ColorfulXL-Lightning
  • playgroundai/playground-v2-512px-base
  • playgroundai/playground-v2-1024px-aesthetic
  • playgroundai/playground-v2.5-1024px-aesthetic
  • stabilityai/sd-turbo
  • stabilityai/sdxl-turbo
  • thibaud/sdxl_dpo_turbo
  • SG161222/RealVisXL_V4.0_Lightning
  • cagliostrolab/animagine-xl-3.1
  • aipicasso/emi-2
  • IDEA-CCNL/Taiyi-Stable-Diffusion-XL-3.5B
  • dataautogpt3/OpenDalleV1.1
  • dataautogpt3/ProteusV0.4
  • dataautogpt3/ProteusV0.4-Lightning
  • etri-vilab/koala-1b
  • etri-vilab/koala-700m
  • digiplay/AbsoluteReality_v1.8.1
  • segmind/Segmind-Vega
  • segmind/SSD-1B
  • gsdf/Counterfeit-V2.5
  • stabilityai/stable-diffusion-xl-base-1.0
  • runwayml/stable-diffusion-v1-5
  • nitrosocke/Ghibli-Diffusion

Help

• Usage :
  • (optional) Modify the settings to use another model, generate several images in a single run or change dimensions of the outputs
  • (optional) Select a LoRA model and set its weight
  • Fill the prompt with what you want to see in your output image
  • Fill the negative prompt with what you DO NOT want to see in your output image
  • Click the Generate button
  • After generation, generated images are displayed in the gallery. Save them individually or create a downloadable zip of the whole gallery.
• Models :
  • You could place huggingface.co or civitai.com Stable diffusion based safetensors models in the directory ./biniou/models/Stable Diffusion. Restart Biniou to see them in the models list.
• LoRA models :
  • You could place huggingface.co or civitai.com Stable diffusion based safetensors LoRA models in the directory ./biniou/models/lora/SD or ./biniou/models/lora/SDXL (depending on the LoRA model type : SD 1.5 or SDXL). Restart Biniou to see them in the models list.

Examples

• Prompt : a cute kitten playing with a ball, dynamic pose, close-up cinematic still, photo realistic, ultra quality, 4k uhd, perfect lighting, HDR, bokeh
• Negative prompt : out of frame, bad quality, medium quality, blurry, ugly, duplicate, text, characters, logo
• Output(s) :