Tongyi-MAI/Z-Image-Turbo

#89 opened 4 days ago by

gottaloveit

Any update on base weights?

🤗 ❤️ 16

#88 opened 5 days ago by

nDimensional

This site uses a lot of beautifully rendered, hyper-realistic images generated by AI. They look like ZImage models.

#87 opened 5 days ago by

sccssc

Sharing quantizing code for both text encoder and the transformer

👍 🔥 3

#84 opened 6 days ago by

ebybucuresteanu

Blog post doesn't mention base model

👀 🤗 2

10

#81 opened 7 days ago by

DioxideSiO2

Z-Image Turbo LoRA training with AI Toolkit and Z-Image ControlNet Full Tutorial for Highest Quality

#78 opened 9 days ago by

MonsterMMORPG

mis post

#76 opened 9 days ago by

MonsterMMORPG

Does Z-Image support embedding/textual-inversion–style adapters? If not, why?

👍 2

#74 opened 10 days ago by

PlayAI

逆天。所以reasoning empowered怎么开？

#73 opened 10 days ago by

imoc

When will the Edit model be open-sourced?

➕ 👀 6

#70 opened 10 days ago by

will-wu

Small theta and the text sequence

#69 opened 10 days ago by

liuliu87

this on stable diffusion is insane, well done

#67 opened 11 days ago by

cutycat2000x

我在Android上跑了一下，只编了cpu支持。谁在Android上用过GPU或者NPU推理过这个模型？

#66 opened 11 days ago by

supershui

Why use an LLM as the text encoder instead of a VLM?

#65 opened 11 days ago by

bengen

Quantizing and running a model using a simple Python script

🚀 1

#64 opened 11 days ago by

mrk-kido

🚀 Big News: LoRA Support is Live on ZImageApp!

#63 opened 11 days ago by

zimageapp

The facial features of the people are too similar, with almost no variation, making the probability of repetition too high.

#62 opened 11 days ago by

sccssc

为什么明明没有提示任何人物脸颊的颜色，但是却有很大概率生成这种很难看的红脸呢

🔥 2

#61 opened 12 days ago by

silentstormzc

Strategic Recommendations: macOS Pro Market Support and Discord Channel Integrity

#60 opened 12 days ago by

akos2

Can someone fix this Pinokio Script

#59 opened 12 days ago by

PierrunoYT

context_refiner

#57 opened 12 days ago by

SirZQ

comment incorrect?

#56 opened 12 days ago by

SirZQ

Is there an optimal resolution recommendation?

#55 opened 12 days ago by

Mark-Hou

Will z-image be great at comics?

#54 opened 13 days ago by

gemstonebro

Morse code OCR performs poorly

#51 opened 13 days ago by

haochengyang

Announcement: ComfyUI Flow Match Euler Discrete Scheduler

👍 3

10

#47 opened 14 days ago by

erosdiffusion

GIVE A RELEASE DATE FOR Z-IMAGE-EDIT , OR JUST DROP IT !

🚀 3

#44 opened 14 days ago by

Besion

I'm a complete teapot, please help

👍 1

#43 opened 15 days ago by

ARAN786

Draw Things 和 DiffusionBee 用不了这个模型？

#41 opened 15 days ago by

tychoon

flux2 vae support?

#39 opened 15 days ago by

nxsimon

有人在移动端跑通过这个模型吗？Has anyone run this model on a mobile device?

#38 opened 15 days ago by

supershui

Thank You for your awesome Contribution to OS ✨

🔥 11

#35 opened 16 days ago by

rishappi

Lora question

#31 opened 16 days ago by

vodll

Error while deserializing header: header too small

#30 opened 16 days ago by

LeFakeTotoro

Error on the node "Load CLIP"

#29 opened 16 days ago by

yan1977

latent size

🚀 1

#28 opened 16 days ago by

CemalSahin

Flux2 vs Z-Image: Who is the winner ? Edit model ~

🔥 6

7

#27 opened 16 days ago by

sunnyboxs

i think its still too large !

🔥 1

10

#26 opened 16 days ago by

LeroyDyer

RELEASE THE EDIT ✍️

🚀 7

6

#25 opened 16 days ago by

Besion

z-image models is specially only working with qwen3 4b ?

#24 opened 16 days ago by

pikkaa

fp8 text encoder pls

#23 opened 17 days ago by

JorG941

Draw Things app by LIULIU / (Forge replacement) -- for Macs -- when will there be a Safetensor compatibility ?

#22 opened 17 days ago by

akos2

You are the best

👍 20

#21 opened 17 days ago by

sdfasdfasdfsdfsdf

Will ControlNet be supported in the future?

#20 opened 17 days ago by

badraymen

Can this run with Forge? If not, will there eventually be a version for it?