Home Creators Posts Import Register Favorites Logout

Content

Qwen Image, free and open source, is unchallenged at complex prompts and text on images; these raw SwarmUI thumbnails used Gemini 2.5 Pro prompts.

Shows Qwen Image understanding complex prompts and writing text on generated images as the author's new tool for generating thumbnail images: even low-effort prompting gives excellent results, all unmodified raw generations. Links the 700+ test Qwen Image tutorial and the SwarmUI with ComfyUI install tutorial.


Related posts

All posts in this topic: AI Image Generation and Editing Apps · New to SECourses? Start Here: Best and Most Popular SECourses Posts

Files

Comments

arquinovatos (edited)

Comment edits

2026-09-07 10:00 Can't wait to see a fine tuning tutorial for this one!!! Also, do you think it can change objects as kontext and redux?
2025-08-10 16:11

SECourses

they said they will publish such model hopefully. yes training is my #1 priority

Roni Bliss

Nooo, it's not.... The king of image models was already here, hiding! Its good but it's nowhere near as good as Wan 2.2 for images - Not even close - You're missing out! Not many people know it for images, but I have done rigorous testing and it blows Qwen out the water - Well actually I I will caveat that in saying ... It all depends on what you are looking for , Qwen is better for fantasy style images, It's not good at photo realism, it makes everything too polished and "fantasy" like... Which all the examples you made are. BUT for Photo realism, WAN is the best model of all time. PLUS and its a HUGE plus, Wan is soooooo good for making Loras, it comes up with perfect likeness even with small bad datasets. AND the Loras can be used for making brilliant quality videos. So And using the BEST Lora trainer I just found, AI-Toolkit, which is so easy to use and has an amazing GUI, making them is jut great fun. Anyone looking for Photo real fully uncensored images with the best Loras, check out Wan for images is really the king.

SECourses

just wait until you see my loras on Qwen :D

Josh Baker

how do you make images in wan 2.2, just set to one frame?

Philipp Capetian

Qwen sticks very close to the prompts. The downside to this is that - in my experience - different seeds do not really change the images as before. So multiple generations almost look the same. You need to change the prompt entirely. Or is there something I'm missing out?

SECourses

you are probably right. it looks like not very much impacted by seed. i still get different outputs but not very wildly different

SECourses

yes but need a better workflow. hopefully i will publish presets soon

Roni Bliss

Yeah set it 1 frame - Check out this video he has work flow there! UNBELIEVAB:LE results. Literally indistinguishable from a real life photos, and Lora training so good, you literally can't go wrong even shitty datasets Wan pulls it out - video here + workflow free : https://www.youtube.com/watch?v=8LCQXxDF16U

SECourses

i will make preset for images very soon hopefully. still qwen training will be better wan training i am pretty confident

Hockey

I had to remove sage attention on the ComfyUI backend in SwarmUI, otherwise Qwen only generated black images for me.

Taiga

you insinuate that you're going to show how to generate prompts with Gemini 2.5... WHERE!? "This tutorial literally shows how these images were generated with Gemini 2.5 Pro made prompts" - literally, where?