This model is trained from scratch using tokenized midi music. I have trained a MidiTok tokeniser (REMI) and its made by spliting multi-track midi into a single track.

Task

Models

Family

—

Status

ListedB

WorkflowCivitai

LTX 2.3 Add Audio to Existing Video by WW

TLDR: You can use LTX 2.3 to introduce audio into existing videos, with limits.

Multi

LTX-Video 2.3

IP-Adapter anime fine tune

IP-Adapter but fine-tuned on anime images. The result is not perfect but definitely better than the non fine-tuned versions (for anime).

Models

Stable Diffusion 1.5

Node packExternal source

comfyui-metadata-booster

Comfy UI extension for manage metadata in media

Node packs

—

Node packExternal source

ComfyUI_MagicQuill

Official ComfyUI Node for Paper - MagicQuill: An Intelligent Interactive Image Editing System

Node packs

—

concept Faceless female+blush

Although I use txt2img to directly generate,I highly recommend using img2img inpaint , as it will affect the composition and style of painting if used directly in the txt2img

Models

Stable Diffusion 1.5

Node packExternal source

ComfyCollectorNodes

A set of nodes I needed and that you can also have, too, as well.

Node packs

—

Gemma 4 E2B GGUF

> [!IMPORTANT] > This model is automatically converted using

Models

—

Node packExternal source

ComfyUI_Sana_WM

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Node packs

—

Node packExternal source

ComfyUI-TP-IMtalker

Comfy UI nodes for IMtalker to run native weights

Node packs

—

Node packExternal source

miniature-lamp

DINO embeddings as a condition to guide the upscaler's denoising process

Node packs

—

Z-Image Turbo t2i / i2i / i2i inpaint - FoxFurEssence Workflow

An efficient, relatively clean z-image Turbo workflow for text2image, image2image, and image2image mask/inpainting. Highly optimized for realism tasks and AI filmmaking.

Text to image

Z-Image Turbo

Node packExternal source