Image generation

4 notes

Images of a blonde girl in a military-style dress made by five AIs, in 5 columns and 2 rows. The top row is character design, the bottom row is main art regenerated from a reference image. From the left, ChatGPT, Gemini, Grok, PixAI, and ComfyUI
AIImage generationAvatarPNGTuber

Which AI is best for making PNGTuber assets?

Comparing ChatGPT, Gemini, Grok, PixAI, and ComfyUI on their free tiers for a PNGTuber's character design, main art from a reference image, and an eyes-closed variant, and working out which AI suits which asset.

The Peraravatar+ editor. The avatar on the left, the settings menu on the right
AIImage generationHand-drawnAvatarPNGTuberStreaming

Making a streaming avatar with Peraravatar+

Making a streaming avatar with the Peraravatar+ PNGTuber: a blank-face base from one AI image, presets for a quick start, your own eye and mouth parts, and a bouncing chest and swinging accessories.

A workflow with a LoRA wired in, and a preview of the generated images
AIImage generationComfyUIR18NSFW 18+

How to generate NSFW images

Choosing a model, wiring a LoRA, and writing prompts that work, plus how to fix what breaks.

Hidden Click to change
The ComfyUI screen
AIImage generationComfyUIWindows

Setting up AI image generation on your own PC

Getting ComfyUI running on Windows: two ways to install it, picking a model and checking its license, and how the nodes fit together.

← All notes