[KongchangAI]
Product

Draw Things

Draw Things is a local AI image generation application optimized for Apple Silicon. It supports local inference with Stable Diffusion series models and includes a built-in JavaScript sandbox environment that supports automation scripts for batch image generation.

Timeline (last 90 days)

Sep 18

MiniMax H3 is now officially supported on Draw Things, allowing Mac and iPad users to run the model on local devices.

Unverified50%
Sep 18

On Draw Things, MiniMax H3 is available in two types and eight quantization precisions.

Unverified50%
Sep 18

The first-and-last-frame version of MiniMax H3 (FLR VA) supports three modes—text-to-video, image-to-video, and first-and-last-frame video—making it the first model on Draw Things to support first-and-last-frame generation.

Unverified50%
Sep 18

The Talmate 3-step acceleration LoRA version optimized by KeyJay is only 182MB in size and can be imported into Draw Things to run.

Unverified50%
Sep 18

It is advised to first run through the workflow at a small size (e.g., 576×384) with fewer frames (e.g., 107 frames), and then gradually increase the size and number of frames.

Unverified50%
Sep 18

The UP host conducted a local real-world test of MiniMax H3 on Draw Things using an M5 iPad Pro with 16GB of memory.

Unverified50%
Sep 18

When Draw Things supports audio plus images as joint input conditions, it is expected to enable the creation of short films exceeding 15 seconds with coherent audio consistency.

Unverified50%

All Facts (10)

Unverified

Mac mini上本地生图单张耗时30秒到2分钟

75%
Unverified

Draw Things has a built-in JS sandbox environment that allows users to write automation scripts to invoke the image generation pipeline for batch generation.

60%
Unverified

Draw Things is a local AI image generation application optimized specifically for Apple Silicon (M-series chips), supporting local inference for the Stable Diffusion series of models.

60%
Unverified

The first-and-last-frame version of MiniMax H3 (FLR VA) supports three modes—text-to-video, image-to-video, and first-and-last-frame video—making it the first model on Draw Things to support first-and-last-frame generation.

50%
Unverified

On Draw Things, MiniMax H3 is available in two types and eight quantization precisions.

50%
Unverified

The Talmate 3-step acceleration LoRA version optimized by KeyJay is only 182MB in size and can be imported into Draw Things to run.

50%
Unverified

It is advised to first run through the workflow at a small size (e.g., 576×384) with fewer frames (e.g., 107 frames), and then gradually increase the size and number of frames.

50%
Unverified

When Draw Things supports audio plus images as joint input conditions, it is expected to enable the creation of short films exceeding 15 seconds with coherent audio consistency.

50%
Unverified

MiniMax H3 is now officially supported on Draw Things, allowing Mac and iPad users to run the model on local devices.

50%
Unverified

The UP host conducted a local real-world test of MiniMax H3 on Draw Things using an M5 iPad Pro with 16GB of memory.

50%

Source Articles