Skip to main content

Play with Stable Diffusion in Five Minutes, Create Your AI Goddess Just with a Browser

Original Video Tutorial​

[Teaching Lazy Pack] Perfection that Midjourney can't do! Get Stable Diffusion done in three minutes! Create your AI goddess for free with just a browser! (No graphics card required)

Open Google Colab​

https://colab.research.google.com/

Click the +code in the upper left corner, and an input box will appear.

Input command:​


!pip install --upgrade fastapi==0.90.1
!git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui
!git clone https://github.com/yfszzx/stable-diffusion-webui-images-browser /content/stable-diffusion-webui/extensions/stable-diffusion-webui-images-browser
!curl -Lo chilloutmixni.safetensors https://huggingface.co/nolanaatama/chomni/resolve/main/chomni.safetensors
!curl -Lo ulzzang-6500.pt https://huggingface.co/nolanaatama/chomni/resolve/main/ulzzang-6500.pt
!mv "/content/chilloutmixni.safetensors" "/content/stable-diffusion-webui/models/Stable-diffusion"
!mv "/content/ulzzang-6500.pt" "/content/stable-diffusion-webui/embeddings"
%cd /content/stable-diffusion-webui
!COMMANDLINE_ARGS="--share --disable-safe-unpickle --skip-torch-cuda-test --no-half-vae --xformers --reinstall-xformers --enable-insecure-extension-access" REQS_FILE="requirements.txt" python launch.py

Click to Execute​

Wait for execution to complete

Modify Configuration​

Execution to the end will throw an error because there is no GPU hardware, so click the hardware configuration modification in the upper right corner.

Change to GPU​

Execute the code again​

After the execution is completed, there will be a temporary domain name. Click to enter, and you can start playing.

Parameter Configuration​

Prompt​

Prompt is the text input to the text-to-image model. Different Prompts have a greater impact on the quality of the generated image.

(8k, RAW photo, best quality, masterpiece:1.2), (realistic, photo-realistic:1.37), ultra-detailed,full body,1 girl, solo,beautiful detailed sky,detailed tokyo street,night,beautiful detailed eyes,beautiful detailed lips,professional lighting, photon mapping, radiosity, physically-based rendering,extremely detailed eyes and face, beautiful detailed eyes,light on face,cinematic lighting, short jacket,hoodie,school uniform,1girl,full body,full-body shot,see-through,looking at viewer,outdoors,((white hair)),

Negative​

Negative is a reverse prompt word, describing what you don't want to appear in the image with text.

EasyNegative, paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, glans,extra fingers,fewer fingers,strange fingers,bad hand,signature, watermark, username, blurry, bad feet,bad leg, duplicate, extra limb, ugly, disgusting, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, blurry,mutated hands and fingers,, EasyNegative, paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, glans,extra fingers,fewer fingers,strange fingers,bad hand,signature, watermark, username, blurry, bad feet,bad leg

Then click Generate

Inject new spells into your pictures​

Stable Diffusion Keyword tag syntax tutorial

stable-diffusion-webui prompt syntax explanation

Finally, post the beauty just generated​