Generate images

Juggernaut XL Ragnarok Settings: NSFW Prompts, Negative Prompt, and ComfyUI Workflow

Dial in Juggernaut XL Ragnarok with tested sampler, steps, CFG and resolution values, copy tasteful non-explicit glamour prompts, build a clean ComfyUI graph with a hires pass, and see which PicassoIA models give similar photoreal results today.

Juggernaut XL Ragnarok Settings: NSFW Prompts, Negative Prompt, and ComfyUI Workflow
Cristian Da Conceicao

Most people who download Juggernaut XL Ragnarok get a plastic, over-sharpened portrait on the first try and blame the model. The model is fine. The settings are usually the problem: a CFG that is too high, a negative prompt copied from a 2023 forum thread, and a resolution the checkpoint was never tuned for. Fix those three things and Ragnarok produces some of the most believable skin and fabric you can get out of a Stable Diffusion XL checkpoint.

This article gives you the numbers that work, a prompt structure for tasteful, non-explicit glamour (swimwear, lingerie, boudoir lighting), a short negative prompt strategy, and a ComfyUI graph you can rebuild in five minutes. You will also see where Ragnarok stands today, and which models on PicassoIA give you similar photoreal results without installing anything.

💡 Adults only, always. Everything below assumes fictional adult subjects, no real people's likenesses, and non-explicit output. Keep it suggestive and beautiful, not pornographic.

What Ragnarok Does Best

Close-up glamour portrait with natural skin texture

Where it came from

Juggernaut XL is a long-running photorealistic checkpoint family from RunDiffusion, built on Stable Diffusion XL. The Ragnarok release (the version with a May 2025 update circulating on model hubs) was tuned to be easier to prompt than the older numbered versions. It leans toward natural light, believable skin pores, and fabric that behaves like fabric.

Its strengths are easy to list:

  • Skin texture that does not look airbrushed when CFG stays low
  • Cinematic lighting that responds well to plain photographic language
  • Clothing detail such as satin sheen, lace trim and linen creases
  • Short prompts, which usually beat long keyword piles

Why it still gets used

Newer image models exist, and some of them follow long prompts better. But Ragnarok runs on modest GPUs, loads fast in ComfyUI, and has a huge library of compatible LoRAs. For people who want local control and no usage limits, that combination is hard to replace.

💡 Availability note: Juggernaut XL Ragnarok is not on PicassoIA yet. If you want similar results without a local install, jump to the PicassoIA section further down.

Best Settings for Ragnarok

Woman on white bed sheets beside a notebook of sampler numbers

Settings reported on the model pages and in RunDiffusion's own notes agree on most points, with a few small disagreements. The table below shows the starting point I recommend, and the range worth testing.

SettingStart hereSafe rangeNotes
SamplerDPM++ 2M SDEDPM++ 2M KarrasSDE gives softer, more filmic skin
Steps3025 to 40Past 40 rarely adds anything
CFG43 to 6Above 6 starts to look plastic
Resolution832 x 1216Other SDXL sizesPortrait ratio suits glamour shots
Negative promptEmptyShort list onlyAdd terms only after a flaw appears
SeedFixed while testingAnyChange one setting at a time

Sampler and scheduler

DPM++ 2M SDE is the safest first choice. In ComfyUI it appears as dpmpp_2m_sde, paired with the karras scheduler. If your images look slightly gritty, try dpmpp_2m with Karras instead. It is a touch cleaner and a touch flatter.

Steps and CFG

Thirty steps is the sweet spot for most portraits. CFG is where people go wrong. Some NSFW-oriented prompt pages recommend 6 to 7, but for Ragnarok that range tends to push contrast and give skin a waxy look. Start at 4. If the model ignores part of your prompt, move to 5, then 6, and stop as soon as the detail appears.

Resolution that works

Generate at 832 x 1216 for portraits and 1216 x 832 for landscape scenes. Going straight to 2048 pixels on the long edge usually produces doubled limbs and stretched faces. Generate small, then upscale (more on that in the workflow section).

NSFW Prompts That Stay Tasteful

Low-angle beach glamour photograph at golden hour

A prompt structure that holds up

Ragnarok responds best to photographer language. Build the prompt in this order:

  1. Subject and pose: age range, hair, expression, what she is doing
  2. Clothing: one or two specific items with materials (satin, lace, linen)
  3. Setting: a real place, not a mood
  4. Light: direction and quality
  5. Camera: lens, aperture, film stock

That ordering keeps the important words early, where SDXL checkpoints give them the most weight.

Three prompts to copy

Boudoir morning

photo of a woman in her late twenties, wavy chestnut hair, light freckles, champagne silk robe slipping off one shoulder, lace lingerie, reclining on white linen daybed, sheer curtains, golden morning light from the left, 85mm f/1.8, shallow depth of field, Kodak Portra 400, film grain, natural skin texture

Beach glamour

photo of a woman in a cream bikini and sheer linen sarong, white sand beach, golden hour backlight, hair blowing in sea breeze, low angle, 50mm f/1.8, rim light on shoulders, slight skin sheen, film grain

Library evening

photo of a woman in a deep red satin slip dress, seated on a velvet armchair, brass lamp, leather books, single warm tungsten light from the right, 70mm f/2, silk highlights, visible skin pores

Notice what is missing: no "masterpiece", no "8k uhd", no "best quality". Ragnarok does not need those tokens, and piling them on tends to add contrast and sharpening you then have to remove.

Lighting words that sell realism

Word or phraseWhat it does
golden hour backlightWarm rim light, soft shadows
window light from the leftDirectional, flattering falloff
single tungsten lampMoody, warm, contained
overcast soft lightEven skin, low contrast
film grain, Portra 400Gentle color, natural noise

Woman in red satin slip dress on a velvet armchair

Negative Prompt: Less Is More

Start with it empty

Official guidance for the Juggernaut line has been consistent for a while: begin with no negative prompt. That surprises people who grew up on old Stable Diffusion 1.5 lists with forty terms, but modern SDXL checkpoints are trained to avoid the usual mess on their own. A huge negative prompt also changes the whole image, because every term pulls the latent away from something.

Run your first batch with the field blank. Look at what actually goes wrong.

Short lists for known flaws

Once you see a specific problem, add only the term that targets it. Here is a short toolbox:

Problem you seeAdd to negative prompt
Waxy skinplastic skin, airbrushed
Over-saturated colorsoversaturated
Odd fingersdeformed hands
Flat, cartoon feelillustration, painting
Stray text or markswatermark, text

A good working negative prompt for glamour photos is rarely longer than this:

plastic skin, oversaturated, deformed hands, watermark

💡 Test one term at a time. Fix the seed, add one word, generate, compare. Five minutes of this beats an hour of copying lists.

ComfyUI Workflow, Node by Node

Creator at a desk looking at a node graph on a widescreen monitor

The base graph

You need only seven nodes for a clean first image. Connect them in this order:

  1. Load Checkpoint: select the Ragnarok file
  2. CLIP Text Encode (positive): your prompt
  3. CLIP Text Encode (negative): empty, or your short list
  4. Empty Latent Image: width 832, height 1216, batch 1
  5. KSampler: the settings below
  6. VAE Decode: uses the VAE from the checkpoint
  7. Save Image

KSampler values:

seed: fixed while testing
steps: 30
cfg: 4
sampler_name: dpmpp_2m_sde
scheduler: karras
denoise: 1.0

Leave the CLIP layer settings at default. SDXL checkpoints do not need the clip-skip tweak that older 1.5 models relied on.

The hires fix pass

This is the step that separates a decent image from a sharp one. After the first KSampler, add:

  1. Upscale Latent By with a factor of 1.5
  2. A second KSampler with the same model and prompts
  3. Settings on the second pass: steps 20, CFG 4, denoise 0.40 to 0.50
  4. Then VAE Decode and Save Image

Woman in a lace bodysuit at a loft window at dawn

A denoise of 0.45 keeps the composition while adding pore and fabric detail. Go above 0.6 and the face can change between passes. For a final 2x or 4x enlargement after that, a dedicated upscale model node works well, or you can send the image to a super resolution tool afterwards.

Fixing hands and faces

Hands are still the weak spot. Two fixes work reliably:

  • Inpaint only the hand with a low denoise (0.35 to 0.5) and a prompt like "natural hand, relaxed fingers"
  • Change the pose so hands hold something simple, such as a bracelet, a glass or a fabric edge

Close-up of hands adjusting a gold bracelet with natural skin texture

Giving the hands a job in the prompt is a cheap trick, and it works more often than any negative term.

Common Mistakes and Fixes

Woman at a rooftop pool bar in a black halter swimsuit

MistakeWhat you seeFix
CFG at 7 or higherWaxy skin, harsh contrastDrop to 4 or 5
Huge negative promptMuddy, washed-out imageEmpty it, add one term at a time
Generating at 2048 pxDoubled limbs, stretched facesUse 832 x 1216 plus a hires pass
Quality-token spamOver-sharpened lookRemove "masterpiece" and "8k"
Changing many settings at onceNo idea what helpedFix the seed, change one thing
Vague clothing wordsGeneric outfitsName the material and color

Another quiet mistake: mixing too many LoRAs. Two at a weight of 0.5 to 0.7 is plenty. Three or more fights the base model, and skin goes first.

How to Get Similar Results on PicassoIA

Running ComfyUI locally means managing checkpoints, drivers and VRAM. If you want similar photoreal glamour output in a browser, Seedream 4.5 on PicassoIA is the first model I would reach for. It handles skin, fabric and light very well, and it accepts the same photographer-style prompts shown above.

Woman in an open white shirt over a rust bikini in a Mediterranean courtyard

Steps with Seedream 4.5

  1. Open the Seedream 4.5 page on PicassoIA.
  2. Paste one of the prompts from the NSFW section above. Drop the negative prompt idea: describe what you want instead of what you do not.
  3. Pick a portrait or landscape aspect ratio to match the 832 x 1216 shape you would use locally.
  4. Generate, then adjust one detail at a time: lens, light direction or clothing material.
  5. Send the best result to PicassoIA Image Editor Pro to fix small flaws such as a hand, a strap or the background, with unlimited generations so you can iterate freely.

💡 Parameter tip: Seedream rewards specific, short sentences. "Champagne silk robe, golden window light from the left, 85mm f/1.8" works better than a long list of adjectives.

Other models worth trying

Ragnarok is not on PicassoIA yet; for similar results today, try these alternatives:

ModelBest forWhy try it
Seedream 4.5Glamour portraits, fabric detailSharp, natural, follows prompts closely
PicassoIA Image Editor ProFixing and restyling imagesUnlimited generations, fast edits
RealVisXL v3.0 TurboFast SDXL-style realismClosest to the Ragnarok feel in speed and look
Z Image TurboQuick draftsSharp results in seconds

If you like the ControlNet-style pose control that ComfyUI users enjoy, SDXL Multi Controlnet LoRA is worth a look too. Browse everything else at picassoia.com/en/all-models.

Quick Reference Card

Copy this into a note next to your ComfyUI window:

  • Checkpoint: Juggernaut XL Ragnarok
  • Sampler: DPM++ 2M SDE with Karras
  • Steps: 30 (hires pass: 20)
  • CFG: 4 (range 3 to 6)
  • Size: 832 x 1216, then Upscale Latent By 1.5
  • Hires denoise: 0.45
  • Negative prompt: empty first, then one term at a time
  • Prompt order: subject, clothing, setting, light, camera, film stock
  • LoRAs: two at most, weight 0.5 to 0.7

Make Your Own Images Today

The honest summary: Ragnarok rewards restraint. Low CFG, a short prompt, a nearly empty negative field and a gentle hires pass will beat any giant settings dump. Try the three prompts above, change one variable per run, and keep notes.

If you would rather skip the install and get straight to results, open Seedream 4.5 on PicassoIA, paste a prompt, and see how fast a photoreal glamour image appears. Then refine it in Image Editor Pro, which has no cap on generations, and browse every available model at picassoia.com/en/all-models. Pick a prompt, press generate, and start building your own set.

Share this article

Choose your language

FreeCreate AI Images and VideosFree, No Credit CardFree Generations to StartSeedance 2.5 Lite IncludedStart Free Now