⚡ Webinar | Directing Video Models: MiniMax H3 ft. Luka Tisler. Join now ➤

Image prompt upsampling with LLMs

Enhance your prompts to generate higher quality images

Image

llm

prompt upsampling

t2i

z-image

469

Gen time: ~24 secs

simplesmenteia

Nodes & Models

ComfyUI Official

PrimitiveStringMultiline

CLIPLoader

ernie-image-prompt-enhancer.safetensors

Ver Private

Comm Use

qwen_3_4b-bf16.safetensors

Ver Private

Comm Use

Note

VAELoader

ae.safetensors

Ver Private

Comm Use

UNETLoader

z_image_turbo_bf16.safetensors

Ver Private

Comm Use

EmptyImage

LoraLoaderModelOnly

zit\zImageT_zidiusArt_melancholy.safetensors

ModelSamplingAuraFlow

PreviewAny

CLIPTextEncode

ConditioningZeroOut

KSampler

VAEDecode

SaveImage

Video tutorial (original audio in pt-BR, auto dub available):

Related links:

floyoofficial

26.2k

Image

Marketing

Photography

Production

Text2Image

z-image

Z-Image Turbo

Fast Image Generation in Seconds

Z-Image Turbo · Text to Image

Fast Image Generation in Seconds

floyoofficial

11.2k

ai image generator

Image

Image to Image

Text to Image

z-image

Z-Image Turbo

Z-Image Turbo is Alibaba's open-source 6B model that turns a text prompt into photorealistic images in about 8 steps. Type a prompt, or rework an image.

Z-Image Turbo · Text or Image to Image

Z-Image Turbo is Alibaba's open-source 6B model that turns a text prompt into photorealistic images in about 8 steps. Type a prompt, or rework an image.

shizzy

11.3k

Image

text to image

A fast simple workflow to get familiar with open source workflows

Text to Image Quick Start

A fast simple workflow to get familiar with open source workflows

agi

8.6k

Audio

I2V

Image to Video

Minimax H3

Open Weight

Video

Minimax H3を使用したImage to Videoワークフローです。オープンウェイトモデルのためAPIウォレットを消費せず、Load Imageにスタートフレーム画像をアップロードし、aspect_ratio、duration、promptを設定するだけで、すぐに動画生成できます。This is an Image to Video workflow using Minimax H3. Since it uses an open-weight model, it does not consume your API wallet.

Minimax_H3_Image_to_Video_OpenWeight

floyoofficial

28.2k

AiVideo

API

image to video

Video

video generation

wan 2.5

Wan 2.5: Image to Video with Audio

floyoofficial

16.7k

API

gemini 3 pro

Image

Image2Image

typography

Google just released Nano Banana Pro, and honestly, it's a pretty big step up from the original Nano Banana. The main thing? It can actually put legible text in images now. Like, real text that you can read, not the garbled nonsense most AI models spit out.

Nano Banana Pro: Generate & Edit Images

floyoofficial

15.8k

VFX

Video

Video2Video

Video Production

Wan2.6

Wan 2.6 Reference to Video

Image prompt upsampling with LLMs

Enhance your prompts to generate higher quality images

Image

llm

prompt upsampling

t2i

z-image

Nodes & Models

ComfyUI Official

PrimitiveStringMultiline

CLIPLoader

ernie-image-prompt-enhancer.safetensors

qwen_3_4b-bf16.safetensors

Note

VAELoader

ae.safetensors

UNETLoader

z_image_turbo_bf16.safetensors

EmptyImage

LoraLoaderModelOnly

zit\zImageT_zidiusArt_melancholy.safetensors

ModelSamplingAuraFlow

PreviewAny

CLIPTextEncode

ConditioningZeroOut

KSampler

VAEDecode

SaveImage

Discover more workflows

Discover more workflows