chris-hayes
multidimensional beings,himalayas,mist,epic,matte painting,emil melmoth,zdzislaw belsinki,craig mullins,yoji shinkawa,trending on artstation,
Generated with Stable Diffusion AI v1.4.
Prompt: "multidimensional beings,himalayas,mist,epic,matte painting,emil melmoth,zdzislaw belsinki,craig mullins,yoji shinkawa,trending on artstation,"
Seed: 955
CFG usually either 7, or 14
Image was upscaled with Topaz Gigapixel
Gigapixel config:
- Upscale: 2x
- Mode: standard
- De-noising: 0
- Blur Reduction: 20
- Face recovery: 15
Workflow:
- Generate a ton of 10-20 step "rough drafts" in Google Colab
- Grab the seeds of the good-ish ones
- Rerun in Google Colab with 60-100 steps with the seeds
- Send the good images to Google Drive
- Pull those images into Gigapixel AI and export with standard settings
- Finally, also send them through Sharpen AI, often with "Too soft - Normal" and 30-70 added grain. This step isn't that crucial, but it does help a tiny bit.
- Post to flikr with JS scripts to automate this description :)
Start making with Stable Diffusion on the official web UI: beta.dreamstudio.ai/
You get 200 free credits. Alternatively, find a Google Colab to make images at a cheaper rate. Mine personal one is too personalized to publicly share.
Join the Stable Diffusion community on Discord: discord.gg/stablediffusion
multidimensional beings,himalayas,mist,epic,matte painting,emil melmoth,zdzislaw belsinki,craig mullins,yoji shinkawa,trending on artstation,
Generated with Stable Diffusion AI v1.4.
Prompt: "multidimensional beings,himalayas,mist,epic,matte painting,emil melmoth,zdzislaw belsinki,craig mullins,yoji shinkawa,trending on artstation,"
Seed: 955
CFG usually either 7, or 14
Image was upscaled with Topaz Gigapixel
Gigapixel config:
- Upscale: 2x
- Mode: standard
- De-noising: 0
- Blur Reduction: 20
- Face recovery: 15
Workflow:
- Generate a ton of 10-20 step "rough drafts" in Google Colab
- Grab the seeds of the good-ish ones
- Rerun in Google Colab with 60-100 steps with the seeds
- Send the good images to Google Drive
- Pull those images into Gigapixel AI and export with standard settings
- Finally, also send them through Sharpen AI, often with "Too soft - Normal" and 30-70 added grain. This step isn't that crucial, but it does help a tiny bit.
- Post to flikr with JS scripts to automate this description :)
Start making with Stable Diffusion on the official web UI: beta.dreamstudio.ai/
You get 200 free credits. Alternatively, find a Google Colab to make images at a cheaper rate. Mine personal one is too personalized to publicly share.
Join the Stable Diffusion community on Discord: discord.gg/stablediffusion