ThinkDiffusionXL
8560°
<think-xl>
Apps that support ModelTrends tags let you run/install models by copying this code in your prompt with no setup. Look for our icon in apps that support it, like Prism (below).
Run this model
Offers / Ads
Easy Creator (Prism) Web
Unlimited · flat fee
Best for beginners. Describe what you want in a chat and the picture comes back, no learning curve.
PirateDiffusion Telegram
Unlimited · flat fee
Images and video from a chat, with short commands. The most convenient tool for Telegram users, with a web companion.
Pro studio (SpyGlass) Web
Unlimited · flat fee
Best for power users. Full control over models, settings and workflows in a browser studio.
Discord bot (Vector)
Unlimited · flat fee
Best for communities. Add it to your own server and run any workflow from a channel.
Unified Editor Web
Unlimited · flat fee
One screen for every model and workflow: prompts, references, edits and video, built into your Graydient account.
Civitai Web
Pay per use
Generate on Civitai's own site; every image is paid for with Buzz credits.
Local apps
Requires setup
Set up local programs if your computer has capable hardware.
ModelDuel Web
Pay per use
Generate the same prompt on up to 50 checkpoint/base models at a time.
ThinkDiffusionXL by ThinkDiffusion. ThinkDiffusionXL is the result of our goal to build a go-to model capable of amazing photorealism that's also versatile enough to generate high-quality images across a variety of styles and subjects without needing to be a prompting genius.
Creator notes
ThinkDiffusionXL (TDXL)
ThinkDiffusionXL is the result of our goal to build a go-to model capable of amazing photorealism that's also versatile enough to generate high-quality images across a variety of styles and subjects without needing to be a prompting genius.
You can find it preloaded on
Please leave a review if you're happy with it, this will encourage us to create more and improve on it.
The work
-
Data source: TDXL is trained on over 10,000 diverse images that span photorealism, digital art, anime, and more. The smallest resolution in our dataset is 1365x2048, but many images go up to resolutions as high as 4622x6753. In total, our dataset takes up 42GB.
-
Training: With 1.8 million steps, we’ve put in the work. For comparison, Juggernaut is at 600k steps and RealVisXL is at 348k steps
-
Hand-captioned images: Each image is carefully captioned by hand, enhancing the model's ability to generate accurate and high-quality results from minimal prompts.
-
NSFW capabilities: The model includes over 1,000 tastefully curated NSFW images.
Our thoughts
-
Detail and quality: Most XL models in the Realistic category suffer from poor detail, especially in the background and even in basic features like eyes, teeth, and skin. We believe TDXL outperforms in these areas due to its large, high-quality dataset. For comparison, Juggernaut has about half the image material, and RealVisXL has only 1,700 images. Ultimately, TDXL simply possesses much more "knowledge".
-
Less-Bias: We made sure to use an equal number of images for each style, gender, etc. Other models we tested over the past few months had some kind of bias, sometimes it was bias toward portrait shots, gender bias, certain ethnicities, etc. For instance, Juggernaut has a bias in the Close-Up area, and the Cinematic Light is quite dominant in that model. RealVisXL also has a bias towards Portrait shots. On the other hand, TDXL gives you what you want: Landscape, Midshot, Full Body, Close-Up, Portrait, Sideview, Backview, Action Shots, Cinematic...whatever you want without always being pushed in a certain direction due to a bias.
-
Versatile base: Because of its large balanced quality dataset, TDXL is versatile to serve as a base model for future trainings. You can create new finetunes in entirely different directions, add LoRAs to fill in missing concepts, or do additional trainings with more balanced quality data.
SHA256
A21C9949EFCB8A0218F575AAFF3FD5E8FEDC508CA6757DDB44C5958CB0859F77
ThinkDiffusionXL Popularity Trend
Heat score, last 12 months
Heat score
8,560°
This week
▼
0.5%
8,563° then, 8,560° now
This month
▼
2.2%
8,571° then, 8,560° now
Past year
▼
26.4%
8,700° then, 8,560° now
7,000°
Floor
The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.
+1,329°
Civitai downloads
30,449 downloads of this exact version on Civitai. Downloads are the heaviest ingredient and are counted on a log scale: ten times the downloads adds the same 300°, so a model with a million downloads is not a thousand times hotter than one with a thousand. The six download sources share that one term, split between them in proportion to their counts.
+39°
Generation sites
899 downloads and generation runs of this model's copies on PixAI. Each run counts as one download, and their downloads count like Civitai's; all of it shares the download term.
+489°
Likes
1,821 likes and thumbs up across the sources. A like weighs half a download, on the same log scale.
+50°
Adoption rate
About 4 downloads a day, measured between two readings of the sources, never guessed from a lifetime average. Speed weighs a quarter of the download term, so a fresh surge shows without letting a one-day spike outrank years of use.
+150°
Full model
+150° because this is a full model: a checkpoint, the weights themselves. A LoRA or an embedding is an add-on to someone else's weights and does not outrank a checkpoint of equal popularity.
−497°
Age
−497° because the SDXL weights came out in 2023. Every model inherits the age of the weights it is built on: 150° a year, up to 750°, and it keeps growing until then. Without it the top of the list would be 2022 and 2023 checkpoints on the strength of downloads that had years to pile up.
Show detailed breakdown
Every number on this site can be checked. This model's heat score is 8,560°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.
- 1Start at the floor.Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.7,000°running total
- 2Add the downloads.31,348 download-equivalents in all, from Civitai downloads, Generation sites. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.+1,329° Civitai downloads+39° Generation sites+1,368°8,368°running total
- 3Add the likes.1,821 likes and thumbs up, at half the weight of a download.+489°8,857°running total
- 4Add the adoption rate.About 4 downloads a day right now, measured between two readings, at a quarter of the weight.+50°8,907°running total
- 5Bonus for a full model.A checkpoint carries the weights themselves; add-ons do not outrank one of equal popularity.+150°9,057°running total
- 6Take off the age.The SDXL weights came out in 2023: 150° a year, up to 750°, growing until then.−497°8,560°running total
- =The heat score.Where this model stands on every list of this site. Nothing else adjusts it.8,560°
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
DPM++ 2M Karras
Steps
30
Guidance
7
Seed
2063937052
Size
768x1160
Clip skip
2
Prompt
(((masterpiece))),(((best quality))),highly detailed, cinematic film still 1girl wet tshirt water drops,splash detailed,surreal dramatic lighting shadow (lofi, analog),kodak film by Brandon Woelfel Ryan McGinley,vignette,high budget,bokeh,cinemascope,moody,epic,gorgeous,film grain,grainy, <lora:xl_more_art-full_v1:0.75>,
Settings
Sampler
DPM++ 2M Karras
Steps
40
Guidance
7
Seed
357142759
Size
512x768
Clip skip
2
Prompt
A gritty engraving etching in the style of Gustave Dore, Moses holds a huge stone tablet with the very large and bold number "404" on it , on mount Sinai amidst a storm, uhd, ((the number "404" written on the tablet)), 8k, intense lighting, award winning masterpiece, high contrast, extremely detailed, detailed background, cinematic, complex and multidimensional lighting, <lora:xl_more_art-full_v1:0.6>, <lora:add-detail-xl:0.6>
Negative prompt
worst quality, low quality, ugly, blurry, unaesthetic, dull colors, (watermark, signature), bad hands,
Settings
Sampler
DPM++ 2M Karras
Steps
30
Guidance
7
Seed
1636543672
Size
768x1168
Prompt
android afghan girl photography by Steve McCurry in cyberpunk style,cyberpunk urban scenery,150mm,dlrs,robotic parts,beautiful neon soft light,bioluminescent tattoos,vibrant details,explicit soft mist,beautiful masterwork by head of prompt engineering
Negative prompt
(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4), (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name:1.2), (blur, blurry, grainy), morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur:1.3), (3D ,3D Game, 3D Game Scene, 3D Character:1.1), (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities:1.3)
Settings
Sampler
DPM++ 2M SDE Karras
Steps
28
Guidance
7
Seed
2374393851
Size
768x1024
Prompt
a LED chihuahua with a coat made out of ral-jeans <lora:ral-jeans-sdxl:1> sitting on a ral-jeans throne
Settings
Sampler
Euler a
Steps
28
Guidance
7
Seed
135075191
Size
832x1216
Clip skip
1
Prompt
by Aaron Jasinski, by Ken Sugimori, (by Brian Mashburn, (by Dan Mumford, magical)), magical, cute baby hamster <lora:ral-jeans-sdxl:1> ral-jeans
Negative prompt
bad quality, bad anatomy, worst quality, low quality, low resolution, extra fingers, blur, blurry, ugly, wrong proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image
Settings
Sampler
DPM++ 2M Karras
Steps
30
Guidance
4
Size
1792x2304
Prompt
cinematic film still dramatic side lighting, dramatic intense stare closeup portrait, dark black background, hdr, dramatic beautiful warrior woman with warrior face paintings and blood, viking braids, blue eyes, pelt, skull necklace, shallow depth of field, vignette, highly detailed, high budget Hollywood film, cinemascope, moody, epic, gorgeous
Negative prompt
anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, blur, bokeh
Settings
Sampler
DPM++ 2M Karras
Steps
30
Guidance
8
Seed
3290503291
Size
1152x896
Prompt
Drawing inspiration from 20th century surrealists like Zdislaw Beksinski,M.C. Escher,H.R. Giger, Horrors of the Great War, (Rats,Sentry posts,Hand-to-hand combat,Grenades,Messengers), , Terror, Asymmetry, [dark|light], [life|death], Mangled, abstract geometric shapes, oil on canvas, drybrush
Negative prompt
modern, sci-fi, futuristic, centered, portrait, symmetry, monochrome, black and white, kitschy,superficial,overly literal,trite,naive,mundane reality
Settings
Sampler
DPM++ 2M Karras
Steps
30
Guidance
7
Seed
382626721
Size
1152x896
Prompt
Inspired by Ian Miller's detailed, nature-meets-machine artistry,Wayne England's bold, angular designs, Horrors of the Great War, (Stretcher bearers,Minenwerfer,Shellfire,Shrapnel,Bayonets), g1g3r, <lora:g1g3r:0.4>, Sorrow, Diagonals, [dark|light], [life|death], Ghoulish, limited color palette,mechanical grotesques,high contrast,detailed backgrounds,wild untamed elements,bold silhouettes,grungy textures.
Negative prompt
modern, sci-fi, futuristic, centered, portrait, symmetry, monochrome, black and white, bright and cheerful,airy and light,simplistic,pastel-colored
Run Locally
How to install
What is ComfyUI? A beginner's guide to nodes, workflows and the first graph
Dec 17, 2025
thinkdiffusionxl_v10.safetensors
Downloads are served by Civitai. Some creators ask for a Civitai login first.
![[NoobAI XL EPS v1.1] Yukari Takeba | Persona 3](https://media.modeltrends.ai/concepts/civitai-1374749/thumb_20261008_063351.webp)
![Character Set: [Taimanin Asagi 2 (Game Ver.)] 対魔忍アサギ２～淫謀の東京キングダム～](https://media.modeltrends.ai/concepts/41098/thumb_civitai_None.webp)
ThinkDiffusionXL is a base model for the Stable Diffusion XL 1.0 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion XL 1.0 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
More Stable Diffusion XL 1.0 modelsMore Stable Diffusion XL 1.0 Base Modelsrealisticeffectsbasebase model
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153