Métal Hurlant Comics Moebius, Bilal, Druillet

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

2,650 downloads · 402 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

Atomease

on Civitai

by Atomease - Métal Hurlant (literal translation: "Howling Metal," "Screaming Metal") is a French comics anthology of science fiction and horror comics stories. Originally created in 1974, the anthologies ceased publication in 1987 but revived between 2002 and 2004 in multilingual editions, and then again in 2020.

Creator notes

Métal Hurlant (literal translation: "Howling Metal," "Screaming Metal") is a French comics anthology of science fiction and horror comics stories. Originally created in 1974, the anthologies ceased publication in 1987 but revived between 2002 and 2004 in multilingual editions, and then again in 2020. How to use Lora weight Based on my testing, I recommend trying all weights between 1 and 2 to see which one works best for your use case. How to Craft Effective Prompts for This Model First of all, I recommend that you take inspiration from the images posted by the author of the model. It is not a plug and play LoRA and requires correct prompting. If your image doesn't include any content/style relevant to the LoRA, then it will have NO effect at all. Please note that the words "image" and "illustration" have HUGE weights and should easily trigger the style in case of trouble. If you're looking to get the best results from this model, here are some tips based on an analysis of the language used in the training data: 1. Focus on Key Subjects and Descriptions: - What to Include: The model is most familiar with terms like "scene", "figure", "creature", "background", and "sky". Descriptive words like "large", "red", "intricate", and "mechanical" also play a big role. - Example Prompt: "Create a detailed scene with a large, red mechanical creature in the foreground." 2. Use Common Phrases: - Why It Helps: The model understands certain word pairs and phrases very well because they appeared frequently in the training captions. Using these can make your prompts more natural and effective. - Example Prompt: "The image depicts a fantastical scene set against a vibrant sky." 3. Incorporate Specific Names or Entities: - Targeted Outputs: If your prompt references specific characters, locations, or objects, the model can generate more focused and relevant results. - Example Prompt: "Illustrate a scene featuring a creature in a mechanical environment." 4. Structure Your Prompts Like Descriptions: - Match the Training Style: The model is used to prompts that describe what’s happening in the image, like “The image depicts...”. Mimicking this style can help the model understand and respond better. - Example Prompt: "The image shows a large creature in an intricate, blue-colored scene." 5. Experiment and Refine: - Iterate on Your Prompts: Start with these suggestions, then tweak the words and phrases to see what works best. Small changes can sometimes lead to big improvements in the results. Example prompts you can try with this model: 1. Prompt for a Fantasy Scene: - "Create a vibrant fantasy scene with a large, red creature standing in the foreground against a mechanical background." 2. Prompt for a Detailed Illustration: - "Illustrate a complex figure set against an intricate, blue sky with various mechanical structures in the background." 3. Prompt Featuring a Specific Character: - "Depict the character Moebius exploring a surreal, otherworldly landscape filled with intricate details and a vibrant color palette." 4. Prompt for a Mechanical Creature: - "Show a large, mechanical creature dominating the scene, with intricate patterns and a deep red color palette." 5. Prompt for a Dreamlike Environment: - "Design a dreamlike scene with floating orbs and clouds in the sky, featuring a detailed figure surrounded by an ethereal atmosphere." Dataset Information Top 20 nouns and adjectives by frequency in the dataset: - image: 147 - scene: 80 - figure: 59 - creature: 58 - large: 55 - red: 54 - - sky: 50 - various: 45 - foreground: 44 - intricate: 43 - - palette: 42 - figures: 41 - blue: 40 - overall: 36 - structure: 34 - mechanical: 33 - illustration: 30 - face: 30 Top 20 collocations by frequency in the dataset: - ('to', 'be') - ('The', 'image') - ('appears', 'to') - ('image', 'depicts') - ('color', 'palette') - ('there', 'are') - ('In', 'the') - ('depicts', 'a') - ('the', 'foreground') - ('theres', 'a') - ('dominated', 'by') - ('The', 'overall') - ('seems', 'to') - ('palette', 'is') - ('a', 'large') - ('There', 'are') - ('graphic', 'novel') - ('shades', 'of') - ('is', 'dominated') - ('scene', 'set')

SHA256

D9A2D2D413932577C2AC19CDF39EC868A9D2EDEE5D9FF49979EC1A03B0E67F4A

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Also ranked: #71 Hottest Flux model

Not this creator?

Get your own badge

Métal Hurlant Comics Moebius, Bilal, Druillet Popularity Trend

Heat score, last 12 months

Heat score

8,084°

This week

▲

0.3%

8,085° then, 8,084° now

This month

▲

1.3%

8,089° then, 8,084° now

Past year

▲

30.4%

8,112° 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.

+1,027°

Civitai downloads

2,650 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.

+391°

Likes

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

−334°

Age

−334° because the Flux weights came out in 2024. 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.
2,650 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.
+1,027°
8,027°
running total
3
Add the likes.
402 likes and thumbs up, at half the weight of a download.
+391°
8,418°
running total
4
Take off the age.
The Flux weights came out in 2024: 150° a year, up to 750°, growing until then.
−334°
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 Atomease on

Settings

Sampler

Euler

Steps

Guidance

Seed

1363273546

Size

1280x1920

Prompt

Oceans of molten metal flow through space, ripping apart stars and galaxies as they surge forward like cosmic rivers of destruction. Towering, skeletal structures rise from the galactic floor, their spires made from the bones of fallen worlds. Reality warps as invisible forces tear the sky apart, leaving behind gaping holes where the universe once stood. Out of the void, multi-limbed, insectoid gods crawl, their bodies writhing and reshaping into impossible forms as they consume the last remnants of creation. <lora:atomeaser_v1:1><lora:metal_hurlant_v1:0.5>,<lora:fantastic_planet_v1:0.2>

Render by a6bIp on

Settings

Sampler

Undefined

Steps

Guidance

Seed

1296259653

Size

832x1216

Clip skip

Weight used

Prompt

Morgoth stands on the edge of a jagged cliff, his massive,shiny armored form and horned helmet silhouetted against a fiery, glowing horizon. From an over-the-shoulder view, the scene captures the dark lord gazing upon his endless army marching in perfect formation across a desolate, ominous landscape. The eerie atmosphere is heightened by vibrant, glowing colors that clash with deep shadows,under giant eerie sun, creating a chiaroscuro effect that emphasizes the contrast between light and darkness. The epic scale of the scene is infused with mystery and menace, embodying the dark fantasy essence of Lord of the Rings,reflections,crowd, best quality, masterpiece,detailed,dramatic,over the shoulder view,from behind,(close-up:1.5), main focus on Morgoth, asymmetrical compsition, depth of field, forced perspective,traditional media,frank frazetta,nicola samori,gustave dore, J. r. r. tolkien, best quality,masterpiece,Directional Lighting, Tempera, Asymmetry, Solarized,intricate, highly detailed, high contrast, strong shadows, dry brush, oil on canvas,colorful,cyan,electric purple,chrysolite

Render by a6bIp on

Settings

Sampler

Undefined

Steps

Guidance

3.5

Seed

1574349946

Size

1216x832

Clip skip

Weight used

Prompt

A futuristic black car with an ornate, gothic-inspired design, resting on a wet street, illuminated by neon reflections on the rain-soaked cobblestones. The custom-made vehicle boasts a streamlined body with large, bold, low-profile wheels that exude power and precision. Its intricate metallic details feature sculpted ornamentation, blending gothic elegance with high-tech futurism. Dramatic lighting cuts through the foggy night, casting long shadows and creating a striking color contrast of glowing neon blues and purples against the sleek black surface of the car. The scene combines gothic sci-fi with Renaissance aesthetics, framed as a masterpiece painting of futuristic high-tech beauty.,deep contrasting shadows, gloss, detailed,vibrant,colorful,color contrast,(dramatic lighting),Picture-perfect image, fog,light particles,expressive,cinematic,((no humans)),UHD,absurdes,visionary,scifi noir.neo-renaissance,crimson, yellow and purple,close-up,zoomed,centered

Render by davidricar57407 on