A silly question: do any of these models generate pixels and also vector overlays? I don't see why we need to solve the text problem pixel-for-pixel if we can just generate higher-level descriptions of the text (text, font, font size, etc). Ofc, it won't work in all situations, but it will result in high fidelity for common business cases (flyers, websites, brochures, etc).
“Qwen‑Image: Open‑source 20 B MMDiT model with stunning text rendering and image editing. Effortlessly create bilingual posters, infographics, slides, infill edits, comics.”
Why it works:
Highlights open‑source nature and 20 billion‑parameter strength
Emphasizes its superior multilingual, layout‑aware text rendering
Mentions real‑world use cases: posters, slides, graphics, image editing, comics/info visuals
> In this case, the paper is less than one-tenth of the entire image, and the paragraph of text is relatively long, but the model still accurately generates the text on the paper.
Nope. The text includes the line "That dawn will bloom" but the render reads "That down will bloom", which is meaningless.
Not sure why this isn’t a bigger deal —- it seems like this is the first open-source model to beat gpt-image-1 in all respects while also beating Flux Kontext in terms of editing ability. This seems huge.
Good release! I've added it to the GenAI Showdown site. Overall a pretty good model scoring around 40% - and definitely represents SOTA for something that could be reasonably hosted on consumer GPU hardware (even more so when its quantized).
That being said, it still lags pretty far behind OpenAI's gpt-image-1 strictly in terms of prompt adherence for txt2img prompting. However as has already been mentioned elsewhere in the thread, this model can do a lot more around editing, etc.
The fact that it doesn’t change the images like 4o image gen is incredible. Often when I try to tweak someone’s clothing using 4o, it also tweaks their face. This only seems to apply those recognizable AI artifacts to only the elements needing to be edited.
This may be obvious to people who do this regularly, but what kind of machine is required to run this? I downloaded & tried it on my Linux machine that has a 16GB GPU and 64GB of RAM. This machine can run SD easily. But Qwen-image ran out of space both when I tried it on the GPU and on the CPU, so that's obviously not enough. But am I off by a factor of two? An order of magnitude? Do I need some crazy hardware?
In their own first example of English text rendering, it's mistakenly rendered "The silent patient" as "The silent Patient", "The night circus" as "The night Circus", and miskerned "When stars are scattered" as "When stars are sca t t e r e d".
The example further down has "down" not "dawn" in the poem.
For these to be their hero image examples, they're fairly poor; I know it's a significant improvement vs. many of the other current offerings, but it's clear the bar is still being set very low.
Does anyone know how they actually trained text rendering into these models?
To me they all seem to suffer from the same artifacts, that the text looks sort of unnatural and doesn't have the correct shadows/reflections as the rest of the image. This applies to all the models I have tried, from OpenAI to Flux. Presumably they are all using the same trick?
I’m seriously getting worried that we use models without openly discussing any potential shortcomings they have. We should somewhere have a list of models and their issues.
I love that this is the only thing the community wants to know at every announce of a new model, but no organization wants to face the crude reality of human nature.
That, and the weird prudishness of most american people and companies.
the value is: the absence of text where you expect it, and the presence of garbled text, are dead giveaways of AI generation. i'm not sure why you are being downvoted, compositing text seems like a legitimate alternative.
I’m interested to see what this model can do, but also kinda annoyed at the use of a Studio Ghibli style image as one of the first examples. Miyazaki has said over and over that he hates AI image generation. Is it really so much to ask that people not deliberately train LoRAs and finetunes specifically on his work and use them in official documentation?
It reminds me of how CivitAI is full of “sexy Emma Watson” LoRAs, presumably because she very notably has said she doesn’t want to be portrayed in ways that objectify her body. There’s a really rotten vein of “anti-consent” pulsing through this community, where people deliberately seek out people who have asked to be left out of this and go “Oh yeah? Well there’s nothing you can do to stop us, here’s several terabytes of exactly what you didn’t want to happen”.
I've been playing around with it for the past hour. It's really good but from my preliminary testing it definitely falls short of gpt-image-1 (or even Imagen 3/4) where reasonably complex strict prompt adherence is concerned. Scored around ~50% where gpt-image-1 scored ~75%. Couldn't handle the maze, Schrödinger's equation, etc.
Besides style transfer, object additions and removals, text editing, manipulation of human poses, it also supports object detection, semantic segmentation, depth/edge estimation, super-resolution and novel view synthesis (NVS) i.e. synthesizing new perspectives from a base image. It’s quite a smorgasbord!
Early results indicate to me that gpt-image-1 has a bit better sharpness and clarity but I’m honestly not sure if OpenAI doesn’t simply do some basic unsharp mask or something as a post-processing step? I’ve always felt suspicious about that, because the sharpness seems oddly uniform even in out-of-focus areas? And sometimes a bit much, even.
Otherwise, yeah this one looks about as good.
Which is impressive! I thought OpenAI had a lead here from their unique image generation solution that’d last them this year at least.
Oh, and Flux Krea has lasted four days since announcement! In case this one is truly similar in quality to gpt-image-1.
It's only been a few hours and the demo is constantly erroring out, people need more time to actually play with it before getting excited. Some quantized GGUFs + various comfy workflows will also likely be a big factor for this one since people will want to run it locally but it's pretty large compared to other models. Funnily enough, the main comparison to draw might be between Alibaba and Alibaba. I.e. using Wan 2.2 for image generation has been an extremely popular choice, so most will want to know how big a leap Qwen-Image is from that rather than Flux.
The best time to judge how good a new image model actually is seems to be about a week from launch. That's when enough pieces have fallen into place that people have had a chance to really mess with it and come out with 3rd party pros/cons of the models. Looking hopeful for this one though!
With the notable exception of gpt-image-1, discussion about AI image generation has become much less popular. I suspect it's a function of a) AI discourse being dominated by AI agents/vibe coding and b) the increasing social stigma of AI image generation.
Flux Kontext was a gamechanger release for image editing and it can do some absurd things, but it's still relatively unknown. Qwen-Image, with its more permissive license, could lead to much more innovation once the editing model is released.
I think the fact that, as far as I understand, it takes 40GB of VRAM to run, is probably dampening some of the enthusiasm.
As an aside, I am not sure why for LLM models the technology to spread among multiple cards is quite mature, while for image models, despite also using GGUFs, this has not been the case. Maybe as image models become bigger there will be more of a push to implement it.
It's all too much of cringe. AI creativity space is chock full of cringy cargocult parody of "no such things as bad publicity" strategy. Things on the Internet is reposted to death so what's wrong if we use them what even is copyright. Everybody hates AI generated images sure that's how you get the word out. Pornography drives adoption so let them have some it should work.
Those behaviors might appear correct in an extremely superficial sense, but it is as if they prompted themselves for "man eating cookies" and ended up with what is akin to early Will Smith pasta gifs. Whatever they're doing and assuming it's cookies held in hands, they're not eating them.
> Miyazaki has said over and over that he hates AI image generation
No he has not. He was talking about an AI model that was shown off for crudely animating 3D people in 2016, in a way that he found creepy. If you watch the actual video, you can see the examples that likely set him off here[0].
I spun up an H100 on Voltage Park to give it a try in an isolated environment. It's really, really good. The only area where it seems less strong than gpt-image-1 is in generating images of UI (e.g. make me a landing page for Product Hunt in the style of Studio Ghibli), but other than that, I am impressed.
Given that it was literally a few months ago when these models could barely do text at all, it seems like the bar just gets higher with each advancement, no matter how impressive.
I mean, did you really expect anything more from the internet? Maybe I'm wrong, but hentai, erotic roleplay, and nudify applications seem to still represent a massive portion of AI use cases. At least in the case of ero RP, perhaps the exploitation of people for pornography might be lessened....
> This may be obvious to people who do this regularly
This is not that obvious. Calculating VRAM usage for VLMs/LLMs is something of an arcane art. There are about 10 calculators online you can use and none of them work. Quantization, KV caching, activation, layers, etc all play a role. It's annoying.
But anyway, for this model, you need 40+ GB of VRAM. System RAM isn't going to cut it unless it's unified RAM on Apple Silicon, and even then, memory bandwidth is shot, so inference is much much slower than GPU/TPU.
I believe it's roughly the same size as the model files. If you look in the transformers folder you can see there are around 9 5gb files, so I would expect you need ~45gb vram on your GPU. Usually quantized versions of models are eventually released/created that can run on much less vram but with some quality loss.
> I think the fact that, as far as I understand, it takes 40GB of VRAM to run, is probably dampening some of the enthusiasm.
For PCs I take it one that has two PCIe 4.0 x16 or more recent slots? As in: quite some consumers motherboards. You then put two GPU with 24 GB of VRAM each.
A friend runs this (don't know if the tried this Qwen-Image yet): it's not an "out of this world" machine.
It's on page 14 of the technical report. They generate synthetic data by putting text on top of an image, apparently without taking the original lighting into account. So that's the look the model reproduces. Garbage in, garbage out.
Maybe in the future someone will come up with a method for putting realistic text into images so that they can generate data to train a model for putting realistic text into images.
I too have have been underwhelmed by these pelican on a bicycle creators. We used to use them for company blog art, by lately we've switched to using attributed images from Wikimedia commons.
Social stigma? Only if you listen to mentally ill Twitter users.
It's more that the novelty just wore off. Mainstream image generation in online services is "good enough" for most casual users - and power users are few, and already knee deep in custom workflows. They aren't about to switch to the shiny new thing unless they see a lot of benefits to it.
Even though I didn't see a significant improvement over Imagen3 in adherence, I agree. Initially the page was just getting a bit crowded but now that I've added a "Show/Hide Models" toggle I'll go ahead and make that change.
Also I think you need a 40GB "card", not just 40GB of vram. I wrote about this upthread, you're probably going to need one card, I'd be surprised if you could chain several GPUs together.
If you think diffusing legible, precise text from pure noise is garbage then wtf are you doing here. The arrogance of the it crowd can be staggering at times
I get that if you can imagine something, it exists, and also there is porn of it.
What disappoints me is how aligned the whole community is with its worst exponents. That someone went “Heh heh, I’m gonna spend hours of my day and hundreds/thousands of dollars in compute just to make Miyazaki sad.” and then influencers in the AI art space saw this happen and went “Hell yeah let’s go” and promoted the shit out of it making it one of the few finetunes to actually get used by normies in the mainstream, and then leaders in this field like the Qwen team went “Yeah sure let’s ride the wave” and made a Studio Ghibli style image their first example.
I get that there was no way to physically stop a Studio Ghibli LoRA from existing. I still think the community’s gleeful reaction to it has been gross.
There's no social stigma to using AI image generation.
There is what's probably better described as a bullying campaign. People tried the same thing when synthesizers and cameras were invented. But nobody takes it seriously unless you're already in the angry person fandom.
In practice AI image generation is ubiquitous at this point. AI image editing is also built into all major phones.
40GB is small IMO: you can run it on a mid-tier Macbook Pro... or the smallest M3 Ultra Mac Studio! You don't need Nvidia if you're doing at-home inference, Nvidia only becomes economical at very high throughput: i.e. dedicated inference companies. Apple Silicon is much more cost effective for single-user for the small-to-medium-sized models. The M3 Ultra is ~roughly on par with a 4090 in terms of memory bandwidth, so it won't be much slower, although it won't match a 5090.
Also for a 20B model, you only really need 20GB of VRAM: FP8 is near-identical to FP16, it's only below FP8 that you start to see dramatic drop-offs in quality. So literally any Mac Studio available for purchase will do, and even a fairly low-end Macbook Pro would work as well. And a 5090 should be able to handle it with room to spare as well.
> I think the fact that, as far as I understand, it takes 40GB of VRAM to run, is probably dampening some of the enthusiasm.
40 GB of VRAM? So two GPU with 24 GB each? That's pretty reasonable compared to the kind of machine to run the latest Qwen coder (which btw are close to SOTA: they do also beat proprietary models on several benchmarks).
We are thrilled to release Qwen-Image, a 20B MMDiT image foundation model that achieves significant advances in complex text rendering and precise image editing. To try the latest model, feel free to visit Qwen Chat and choose “Image Generation”.
The key features include:
Superior Text Rendering: Qwen-Image excels at complex text rendering, including multi-line layouts, paragraph-level semantics, and fine-grained details. It supports both alphabetic languages (e.g., English) and logographic languages (e.g., Chinese) with high fidelity.
Consistent Image Editing: Through our enhanced multi-task training paradigm, Qwen-Image achieves exceptional performance in preserving both semantic meaning and visual realism during editing operations.
Strong Cross-Benchmark Performance: Evaluated on multiple public benchmarks, Qwen-Image consistently outperforms existing models across diverse generation and editing tasks, establishing a strong foundation model for image generation.
Performance
We present a comprehensive evaluation of Qwen-Image across multiple public benchmarks, including GenEval, DPG, and OneIG-Bench for general image generation, as well as GEdit, ImgEdit, and GSO for image editing. Qwen-Image achieves state-of-the-art performance on all benchmarks, demonstrating its strong capabilities in both image generation and editing. Furthermore, results on LongText-Bench, ChineseWord, and TextCraft show that it excels in text rendering—particularly in Chinese text generation—outperforming existing state-of-the-art models by a significant margin. This highlights Qwen-Image’s unique position as a leading image generation model that combines broad general capability with exceptional text rendering precision.
Demo
One of Qwen-Image’s outstanding capabilities is its ability to achieve high-fidelity text rendering in different scenarios. Let’s take a look at the following Chinese rendering case:
The model not only accurately captures Miyazaki’s anime style, but also features shop signs like “云存储” “云计算” and “云模型” as well as the “千问” on the wine jars, all rendered realistically and accurately with the depth of field. The poses and expressions of the characters are also perfectly preserved.
Let’s look at another example of Chinese rendering:
The model accurately drew the left and right couplets and the horizontal scroll, applied calligraphy effects, and accurately generated the Yueyang Tower in the middle. The blue and white porcelain on the table also looked very realistic.
So, how does the model perform on English? Let’s look at an English rendering example:
Bookstore window display. A sign displays “New Arrivals This Week”. Below, a shelf tag with the text “Best-Selling Novels Here”. To the side, a colorful poster advertises “Author Meet And Greet on Saturday” with a central portrait of the author. There are four books on the bookshelf, namely “The light between worlds” “When stars are scattered” “The slient patient” “The night circus”
In this example, the model not only accurately outputs “New Arrivals This Week”, but also accurately generates the cover text of four books: “The light between worlds”, “When stars are scattered”, “The slient patient”, and “The night circus”.
Let’s look at a more complex case of English rendering:
A slide featuring artistic, decorative shapes framing neatly arranged textual information styled as an elegant infographic. At the very center, the title “Habits for Emotional Wellbeing” appears clearly, surrounded by a symmetrical floral pattern. On the left upper section, “Practice Mindfulness” appears next to a minimalist lotus flower icon, with the short sentence, “Be present, observe without judging, accept without resisting”. Next, moving downward, “Cultivate Gratitude” is written near an open hand illustration, along with the line, “Appreciate simple joys and acknowledge positivity daily”. Further down, towards bottom-left, “Stay Connected” accompanied by a minimalistic chat bubble icon reads “Build and maintain meaningful relationships to sustain emotional energy”. At bottom right corner, “Prioritize Sleep” is depicted next to a crescent moon illustration, accompanied by the text “Quality sleep benefits both body and mind”. Moving upward along the right side, “Regular Physical Activity” is near a jogging runner icon, stating: “Exercise boosts mood and relieves anxiety”. Finally, at the top right side, appears “Continuous Learning” paired with a book icon, stating “Engage in new skill and knowledge for growth”. The slide layout beautifully balances clarity and artistry, guiding the viewers naturally along each text segment.
In this case, the model needs to generate 6 submodules, each with its own icon, title, and corresponding introductory text. Qwen-Image has completed the layout.
What about smaller text? Let us test it:
A man in a suit is standing in front of the window, looking at the bright moon outside the window. The man is holding a yellowed paper with handwritten words on it: “A lantern moon climbs through the silver night, Unfurling quiet dreams across the sky, Each star a whispered promise wrapped in light, That dawn will bloom, though darkness wanders by.” There is a cute cat on the windowsill.
In this case, the paper is less than one-tenth of the entire image, and the paragraph of text is relatively long, but the model still accurately generates the text on the paper.
What if there are more words? Let’s try a harder case:
You can see that the model has completely generated a complete handwritten paragraph on the glass plate.
What if it’s bilingual? For the same scenario, let’s try this prompt:
一个穿着"QWEN"标志的T恤的中国美女正拿着黑色的马克笔面相镜头微笑。她身后的玻璃板上手写体写着 “Meet Qwen-Image – a powerful image foundation model capable of complex text rendering and precise image editing. 欢迎了解Qwen-Image, 一款强大的图像基础模型，擅长复杂文本渲染与精准图像编辑”
As you can see, the model can switch between two languages at any time when rendering text.
Qwen-Image’s text capabilities make it easy to create posters, such as:
A movie poster. The first row is the movie title, which reads “Imagination Unleashed”. The second row is the movie subtitle, which reads “Enter a world beyond your imagination”. The third row reads “Cast: Qwen-Image”. The fourth row reads “Director: The Collective Imagination of Humanity”. The central visual features a sleek, futuristic computer from which radiant colors, whimsical creatures, and dynamic, swirling patterns explosively emerge, filling the composition with energy, motion, and surreal creativity. The background transitions from dark, cosmic tones into a luminous, dreamlike expanse, evoking a digital fantasy realm. At the bottom edge, the text “Launching in the Cloud, August 2025” appears in bold, modern sans-serif font with a glowing, slightly transparent effect, evoking a high-tech, cinematic aesthetic. The overall style blends sci-fi surrealism with graphic design flair—sharp contrasts, vivid color grading, and layered visual depth—reminiscent of visionary concept art and digital matte painting, 32K resolution, ultra-detailed.
Since we can make posters, of course we can also make PPTs directly. Let’s look at a case of making PPTs in Chinese:
In fact, beyond text processing, Qwen-Image also excels at general image generation, supporting a wide range of artistic styles. From photorealistic scenes to impressionistic paintings, from anime styles to minimalist designs, the model flexibly responds to a wide range of creative prompts, becoming a versatile tool for artists, designers, and storytellers. We will describe these in detail in our technical report.
In terms of image editing, Qwen-Image supports a variety of operations, including style transfer, additions, deletions, detail enhancement, text editing, and character pose adjustment. This allows even ordinary users to easily achieve professional-level image editing. We will describe these in detail in our technical report.
In summary, we hope that Qwen-Image can further promote the development of image generation, lower the technical barriers to visual content creation, and inspire more innovative applications. At the same time, we also look forward to the active participation and feedback of the community to jointly build an open, transparent, and sustainable generative AI ecosystem.
However, you have mistakenly marked some answers as correct ones in the octopus prompt: only 1 generated image has octopus have sock puppets on all of its tentacles. And you marked that one image as an incorrect one due to sock looking more like gloves.
it seems like the value is that you don't need another tool to composite the text. especially for users who aren't aware of figma/photoshop nor how to use them (many many many people)
Considering they have not released their image, editor weights, I’m not sure how you could make a conclusion that it is better than Flux Kontext aside from the graphs they put out.
But, obviously you wouldn’t do that. Right? Did you look at the scaling on their graphs?
Per 100k image. And it is additionally $0.01 per image. Considering H100 is $1.5 per hour and you can get 1 image per 5s, we are talking about bare-metal cost of ~$0.002 per image + $0.01 license cost.
They have a much better and cleaner dataset than Stable Diffusion & others, so I’d expect it to be better with some kinds of images (photos in particular)
And if you want the text to faithfully follow the surface of the object (ex tattoos) I don't think the post AI gen manual editing approach is going to be so straightforward.
as long as you don't consider the part of the model which understands text as part of the model, and as long as you don't consider copyrighted text content copyrighted :)
People are downvoting you but it's true. Ghibli is just the highest profile studio that creates work in that general style. Arguably most of the highest quality examples of that style are their work. However they're far from the only practitioners.
All of this only really applies to LLMs though. LLMs are memory bound (due to higher param counts, KV caching, and causal attention) whereas diffusion models are compute bound (because of full self attention that can't be cached). So even if the memory bandwidth of an M3 ultra is close to an Nvidia card, the generation will be much faster on a dedicated GPU.
A 3090 + 2xTitanXP? technically i have 48, but i don't think you can "split it" over multiple cards. At least with Flux, it would OOM the Titans and allocate the full 3090
Oh right, I forgot some diffusion models can't offload / split layers. I don't use vision generation models much at all - was just going off LLM work. Apologies for the potential misinformation.
HF does this for ggufs, and it’ll show you what quantizations will work on the GPU(s) you’ve selected. Hopefully that feature gets expanded to support more model types.
Useless AI art (which is almost all of it) is not like the camera or the synthesizer, it's closer to when 50-60yo moms were sharing Minion memes on facebook: cringe and tasteless. It getting better won't make it more accepted, it will simply make people suspect of actual art until no one really gives a chance to any of it.
There absolutely is - everytime someone uses an AI image in a presentation slide, or in an article to illustrate the point, everybody just rolls their eyes - in my opinion a stock photo or even nothing is preferable to a low effort AI image.
I've been bugging them about this for a while. There are repos that contain multiple model weights in a single repo which means adding up the file sizes won't work universally, but I'd still find it useful to have a "repo size" indicator somewhere.
My wife and I started a children’s jewelry business, and I’ve wanted to use AI to show children wearing our jewelry. Every time I try, I get either ridiculous results or hit some artificial censorship wall about making images with children.
I would really like to find a way to do this (either online or locally) if anyone has any tips for giving a model some images of real jewelry with dimensions (and if needed even photographed or generated children) and having the model accurately place the jewelry on the kids.
Ah, you're right: it doesn't have dedicated FP8 cores, so you'd get significantly worse performance (a quick Google search implies 5x worse). Although you could still run the model, just slowly.
Any M3 Ultra Mac Studio, or midrange-or-better Macbook Pro, would handle FP16 with no issues though. A 5090 would handle FP8 like a champ and a 4090 could probably squeeze it in as well, although it'd be tight.
Your argument might actually be suggesting that you don't like art in general more than that there is a stigma against AI. If there is no value in artisanal art that differentiates it from AI-produced works and therefore both will be discarded as the quality converges, what was supposed to be the value in art to start with?
I think it’s revolutionary. My use case has been creating visuals for use in various VDMX workflows. One cool trick I’ve found has been generating starter images with green screens and then putting those into my local LTX video creation workflow, then using VDMX built a chroma layer with the green screen video and go from there, lots and lots of creative fun. So no not useless AI art.
So far, the times had allowed artworks to be proxies for the artistry behind them; the artwork itself conveyed enough information to appreciate it. But as forgery of the art process itself spreads, that signal disappears and artworks, out of context, simply are. The artwork is still necessary, but now insufficient, to understand and appreciate its artistry, because there might not be any, or at least not any intentional one.
I've qualified with "useless" for a reason. It's cool if you've got a novel use case, but so far I think most uses of AI art are either uncanny filler for blogs and slides; or a driver for the deprofessionalization and commoditization of artworks, with AI art producers flooding art sites to fight regular artists for attention, and industry forcing artists to paint over AI generated works (already common in mobile games) until their cheaper substitutes can replace them, and their next job forces them to set art aside.
Unless I missed something just from skimming their tutorial it looks like they can do parallelism to speed things up with some models, not actually split the model (apart from the usual chunk offloading techniques).
Nah, that won’t gain you much (if anything?) over just doing the layer swaps on RAM. You can put the text encoder on the second card but you can also just put it in your RAM without much for negatives.
Responding to myself, as I realized that my post above feels too dismissive. Being a long time privacy advocate for non-tech-adjacent people, I'm perfectly aware about my bubble and biases. For any normal person, anything I say about digital privacy sounds absolutely abstract and detached from real life, where convenience and low effort dominates everything else. Even in 2025 with all political shenanigans, they just fail to see the link and how it applies to their life. AI imagegen is the same from my observations, most concerns are contained in a tiny bubble of perpetually online people. Not even all artists share the loud opinions (for reference, I used to manage a couple hundred artists), especially not VFX and 3D folks. And that tiny bubble only really exists in the anglosphere - you'll see a completely different picture in other cultural bubbles. There's absolutely no stigma of any kind outside of it.
What experience do you want to point too? I've never seen an artist streaming where they can draw something equivalent to a good piece of AI artwork in 20 minutes. Their advantage right now comes from a higher overall cap on quality of the work. Minute for minute, AIs are much better. It is just that it is pointless giving a typical AI more than a a little time on a GPU because current models can't consistently improve their own work.
Because it is extremely time consuming (and expensive) to do that. The logistics are very challenging with finding a variety of child models, environments/studio, outfits, lighting, cameras, photo processing, etc...
And then you have to do it all over again every few months as the products and the seasons change!
