On Fire

Best for beginners. Describe what you want in a chat and the picture comes back, no learning curve.

PirateDiffusion Telegram

Pro studio (SpyGlass) Web

Images and video from a chat, with short commands. The most convenient tool for Telegram users, with a web companion.

Best for power users. Full control over models, settings and workflows in a browser studio.

Discord bot (Vector)

Best for communities. Add it to your own server and run any workflow from a channel.

Unified Editor Web

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.

Rent a GPU on the cloud

Graydient Cloud GPU

11,463 downloads · 1,468 likes on Civitai

Flat fee, unlimited use. This model installs with one click.

RunPod Cloud GPU

Charged by the minute

Rent a GPU by the minute and set the model up yourself.

Created by

antonio_riolo2610

on Civitai

Creator notes

Get early access to build and test build, be able to try all epochs and test them by yourself on or contact me for support on Discord To support me you can buy me a coffe at Training settings: 35 images, 20 steps, 15 epochs, you find many epochs (with test images using plot xy script) on my while supporting me. Recommended settings: - Make sure you are aware on the usage instructions of LORA - Sampler: DPM++ SDE Karras (Recommended for best quality, you may try other samplers) - CFG Scale : 5 to 10 - LORA weight for txt2img: reccomended 0.4-0.7. - Keys: human on fire, horse on fire, animal on fire, angel on fire, skull on fire, red fire, blue fire This is a very hard to use model. In my experience, to generate the images i posted i had to try a lot of stuff, changing weights and doing many plot xy. I'm going to post epoch 10 but as far as i could see different prompt need different epoch to work well with, in fact many of the images are with different epoch so you will not be able to replicate it excatly by copying the prompt and using another epoch. Wrong weights or wrong epoch will give artifacts or no fire at all. Doesn't work well with many loras in it, the only lora i managed to let it work with is my Luxury Dress model that you will find in many images posted. Most of the training images have monochrome background, it's not easy to make it generate an image with the background you want, not without artifacts. Considering all of this, if you manage to make it work it can generate amazing images, i'll wait a good prompter to post great images about this model, i'm very curious. And remember you can find all epochs in my Patreon, epoch 10 gave best result in most images but sometime a more trained or a less trained epoch gave best results, if you like the concept you should try them all! Enjoy! If you'd like to support my efforts and have access to early and bleeding edge builds, please think about joining my Patreon:

Trigger words

human on fire

animal on fire

horse on fire

angel on fire

skull on fire

red fire

blue fire

bird on fire

SHA256

B20354DE3BA153F04C3F6CF829ED0FC356BA6D3E80F7A5F451DDBCC81AAA8D75

On Fire Popularity Trend

Heat score, last 12 months

Heat score

8,084°

This week

▬

0.0%

8,086° then, 8,084° now

This month

▼

0.2%

8,091° then, 8,084° now

Past year

▼

2.0%

8,168° then, 8,084° 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.

+1,218°

Civitai downloads

11,463 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.

+475°

Likes

1,468 likes and thumbs up across the sources. A like weighs half a download, on the same log scale.

−609°

Age

−609° because the SD15 weights came out in 2022. 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 8,084°, 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.

1
Start 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
2
Add the downloads.
11,463 download-equivalents in all, from Civitai downloads. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.
+1,218°
8,218°
running total
3
Add the likes.
1,468 likes and thumbs up, at half the weight of a download.
+475°
8,693°
running total
4
Take off the age.
The SD15 weights came out in 2022: 150° a year, up to 750°, growing until then.
−609°
8,084°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
8,084°

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.

Get this prompt

Render by Animesky on Civitai

Render by antonio_riolo2610 on Civitai

Settings

Sampler

DPM++ 2M SDE Karras

Steps

Guidance

7.5

Seed

3959624418

Size

512x768

Prompt

best quality, professional lighting, super detailed, realistic, beautiful detailed eyes, <lora:cat_20230627113759:0.8> cat, < <lora:on_fire:0.8> fire

Negative prompt

Easy Negative (worst quality:1.2), low quality,

Render by yarosu on Civitai

Settings

Sampler

DPM++ 2M Karras

Steps

Guidance

Seed

2538612825

Size

512x768

Prompt

bird on fire,(blue fire:1.3), good hand,4k, high-res, masterpiece, best quality, head:1.3,((Hasselblad photography)), sharp focus, (cinematic lighting), collarbone, night, soft lighting, dynamic angle, [:(detailed face:1.2):0.2], outside, city,monochrome background, <lora:on_fire10:0.6>

Negative prompt

NG_DeepNagetive_V1_75T,(greyscale:1.2), paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, glans

Render by antonio_riolo2610 on Civitai

Settings

Sampler

DPM++ 2M Karras

Steps

Guidance

Seed

3556372220

Size

512x512

Clip skip

Prompt

chubby man on fire,(red fire:1.3), 4k, high-res, masterpiece, best quality, head:1.3,((Hasselblad photography)), sharp focus, (cinematic lighting), collarbone, night, soft lighting, dynamic angle, [:(detailed face:1.2):0.2], outside, city,monochrome background, <lora:on_fire10:0.6>

Negative prompt

Render by shefchenko on Civitai

Settings

Sampler

DPM++ 2M Karras

Steps

Guidance

Seed

2538612826

Size

512x768

Prompt

Negative prompt

Render by yarosu on Civitai

Settings

Sampler

DDIM

Steps

Guidance

Seed

360405705

Size

1280x1920

Clip skip

Prompt

(masterpiece, 4k ,ultra detailed:1.2),(beautiful face:1.2),(anime:1.2),illustration,(realistic:1), (solo:1.2),(serious,glaring:1.6),(angry:1.2), (looking away,facing away:1.4), (fighting:1.2), (fullbody :1.2),(dutch angle:1), (simple background:1.4),(black background:1.2), (schoolgirl_uniform,black thighhighs,black choker,sneaker:1.1), (black hair,ponytail),(supermodel:1.4), (muscular:1), <lora:hipoly3DModelLora_v10:0.2>, <lora:Cnbeauty4_v1:0.4>, <lora:epiNoiseoffset_v2:1.25>, <lora:on_fire10:0.5>,(human on fire:1.5),(blue fire:1.5)

Negative prompt

EasyNegative,badhandv4,verybadimagenegative_v1.3,By bad artist -neg, (worst quality:1.4), (low quality:1.4) ,( jpeg artifacts, signature,logo,watermark,text:1.3), (elf,loli,child,petite,heterochromia:1.1),(underwear,bag,nipple,nsfw:1.4),(red fire:1.6),(looking at viewer:1.2),

Render by okamuron on Civitai

Settings

Sampler

DPM++ SDE Karras

Steps

Guidance

Seed

3556372220

Size

512x512

Clip skip

Prompt

chubby man on fire,chubby face,(red fire:1.3), 4k, high-res, masterpiece, best quality, ((Hasselblad photography)), sharp focus, (cinematic lighting), collarbone, night, soft lighting, dynamic angle, [:(detailed face:1.2):0.2], outside, city,monochrome background, <lora:on_fire10:0.6>

Negative prompt

Render by antonio_riolo2610 on Civitai

Settings

Sampler

DPM++ 2M Karras

Steps

Guidance

4.5

Seed

2397415331

Size

2048x3456

Prompt

((style of winslow homer):1.3),(style of ryan hewett), (sword:1.3),best quality,,brond girl,knight holds her sword up to own eye,blindfold,black sun,fog,rage,(anger:1.3),storm,wind,desert,rage,she holds her sword up to eye,close-up, , fantasy style, (dark shot:1.17), epic realistic, faded, ,, cinematic, , dramatic light, (intricate details:1.1), complex background, (intricate details:1.12), hdr, (intricate details, hyperdetailed:1.15), white hair,(looking at view:1.2),2B,<lora:LowRA:.6>,<lora:on_fire10:.6>,(ghost:1.3),fighting demon,asura,cross,bow,sacrifice,sea of wepon,iai,,MCSkin complexultra detailed of a beautiful profile intricate details, ultra detailed, , volumetric lighting, 8k post-production,

Negative prompt

sketch, duplicate, ugly, huge eyes, text, logo, worst face, (bad and mutated hands:1.3), (worst quality:2.0), (low quality:2.0), (blurry:2.0), horror, geometry, bad_prompt, (bad hands), (missing fingers), multiple limbs, bad anatomy, (interlocked fingers:1.2), Ugly Fingers, (extra digit and hands and fingers and legs and arms:1.4), ((2girl)), (deformed fingers:1.2), (long fingers:1.2), extra legs

How to install a LoRA: folders, file checks and first use in ComfyUI, Forge, Automatic1111 and Draw Things

Settings

Sampler

DPM++ 2M Karras

Steps

Guidance

Seed

1725024720

Size

512x768

Prompt

a woman wearing luxury dress, azure dress, shiny dress,(blue fire:1.3), good hand,4k, high-res, masterpiece, best quality, head:1.3,((Hasselblad photography)), finely detailed skin, sharp focus, (cinematic lighting), collarbone, night, soft lighting, dynamic angle, [:(detailed face:1.2):0.2], medium breasts, outside, <lora:luxury_dress04:0.3>,<lora:sung02:1>, <lora:on_fire:0.5>

Negative prompt

Run Locally

How to install

Sep 24, 2025

Open Civitai Download

on_fire10.safetensors

144 MB · SafeTensor

Downloads are served by Civitai. Some creators ask for a Civitai login first.

More by this creator

Oversized Sweater/Hoodie

All models by antonio_riolo2610

Chinese weapons（中国兵器）

Latex Dresses Collection By Stable Yogi

POV mouth open and tongue out SOLO