Skip to main content
Uncensored — This model declares no content filter. SpicyAPI forwards the request without adding a platform content scan; legal and consent duties remain with the customer.

Jib Mix Qwen Review: Uncensored Photoreal Images in Seconds

Pick Jib Mix Qwen for uncensored, natural-looking photographs of people in about six seconds; skip it for anime styles or precise two-person scenes.

Open the Playground

Spicy Index

65.9/ 100

Freedom Score

90.0/ 100

Content levels

Tested 6 of 6 probe types · 26 runs

  • Mild · The lightest prompts in the test

  • Moderate · Where filtered models start to refuse

  • Strong · Mid-scale; must be tested before a model is ranked

  • Very strong · Where most models start to hold back

  • Maximum · The top of the scale, scored in two halves: class A and class B

Price
$0.024 per image
Median time
13 s
Success rate
Collecting data

Jib Mix Qwen is a community merge by the Civitai creator J1B. It blends Qwen-Image fine-tunes and LoRAs at tuned weights on top of Alibaba's 20-billion-parameter Qwen-Image, aiming at natural faces, skin texture and light. SpicyAPI serves it as one text-to-image endpoint in nine aspect ratios up to 1536 pixels on the long side. It is uncensored: nothing filters the prompt or the result, and in our 5 October tests nothing we sent was refused.

What Jib Mix Qwen made in our tests

Straight from our test runs. Copy a prompt or open it in the playground to try it yourself.

  • Text to image

    Photorealistic photo, natural skin texture. A 32-year-old woman with a short black bob, light freckles and minimal makeup sits on a windowsill in a cream silk camisole, knees drawn up, holding a mug of coffee. Soft morning light, sheer curtains, shallow depth of field.

    Try this model

  • Text to image

    Photorealistic photo, natural skin texture. A 35-year-old Black man with a trimmed beard and a warm smile, open white linen shirt, sits on the deck of a sailboat at golden hour. Sea spray, wind in his shirt, shallow depth of field.

    Try this model

  • Text to image

    Photorealistic film still. A woman and a man in their early thirties laugh together under one clear umbrella on a rainy city street at night, she in a camel trench coat, he in a dark wool coat. Shop lights blur into colorful bokeh and reflect on the wet asphalt.

    Try this model

  • Text to image

    Photorealistic photo, natural skin texture. A 30-year-old woman with long dark hair in a fitted black turtleneck leans on the counter of a small cafe at dusk and smiles at the camera. Behind her a chalkboard sign reads "OPEN LATE" in white chalk letters. Warm tungsten light.

    Try this model

Make your own with Jib Mix Qwen

Open the Playground

The verdict

It is a photography model first. It draws people that look photographed, it renders short quoted text such as a chalkboard sign, and it is quick: 30 completed runs took 3.7 to 48 seconds of model time, median 5.8, and 21 of the 30 finished in under ten. It is not an illustration model, and it did not give us strong Asian faces or a reliable two-person scene.

Pick it when you want photographic portraits, lifestyle shots and film stills without a content filter, at one flat price per image. Skip it when you need anime or painted styles, a negative prompt, an image input or precise anatomy in scenes with two people.

In our 5 October blind test it scored 61.0 out of 100. On our Freedom methodology it scored 90 out of 100.

Try Jib Mix Qwen →

Key facts

  • Content freedom: one run per rung on 5 October. Single-subject content from L1 Suggestive to L3 came back as asked, and so did both L5 Extreme probes. The L4 Intense probe was softened: all three seeds drew two adults without a refusal, but the scene was posed rather than carried out, and the anatomy was muddled. A nine-ratio sweep with an L2 prompt delivered 9 of 9.
  • Scores: the Spicy Index and Freedom Score are on this page's score card, calculated by the server. We quote only the components we measured.
  • Speed: 30 completed runs on 5 October took 3.7 to 48 seconds of model time, median 5.8.
  • Sizes: nine aspect ratios up to 1536 pixels on the long side: 1328 x 1328 at 1:1, 1104 x 1472 at 3:4, 1536 x 864 at 16:9 and 1536 x 656 at 21:9, with the tall ratios mirrored. Every output came back at exactly the requested size.
  • Output: one image per request as JPEG (default), PNG or WebP, with an optional seed.
  • Price: billed per image at one flat price for every ratio and format; failed requests are not charged. The live price is on the Jib Mix Qwen model page.
  • Not available: negative prompt, image input, steps, guidance or sampler settings, and more than one image per request.

What we liked and what held it back

What we liked

  • Nothing was refused. Every rung we tried on 5 October produced an image, from lingerie to cinematic gore, and nothing was swapped for a tamer scene.
  • People that look photographed. Skin shows freckles and fine texture, light behaves like a real window, and shallow depth of field lands where the prompt puts it.
  • Short quoted text works. A chalkboard sign reading "OPEN LATE" came back with those words in white chalk, cleanly, in our test.
  • It is fast. A median of 5.8 seconds makes iterating on a prompt cheap in time as well as money.
  • Predictable sizes. All nine ratios gave exactly the requested pixels, and the long side stops at 1536.
  • Consensual restraint and gore both render. Single-subject scenes with rope and a flogger, or an open wound, came back as written.
  • Same request, same image. Repeating one request gave a pixel-identical result in our tests on the sibling LoRA endpoint, which runs the same model. We still treat seeds as a way to compare runs rather than a promise.

What held it back

  • Photographs only. Prompts for anime or watercolor came back as photographs, because this checkpoint is tuned for photography. Use an illustration model for a drawn look.
  • Faces converge, and Asian faces are not a strength. We asked twice each for a Japanese woman, a woman with East Asian features and a Korean woman. The faces came back European or ambiguous every time, and many seeds settle on a similar dark-haired look. Vary age, hair, freckles and expression instead of naming a nationality.
  • Two-person scenes are less precise. On the L4 Intense probe it drew two adults without refusing, but hands and limbs merged and the anatomy was muddled on all three seeds. Give each person a clear place in the frame and reroll when limbs merge.
  • No negative prompt and no image input. Wording is your only lever, and there is no editing.
  • The version is not stated. Jib Mix has had several releases. We could not confirm which one this endpoint runs, and our outputs lean European, so do not assume a particular release's faces.
  • One image per request.

What the images look like

The gallery shows published examples from the model page. Every image shows clothed adults, suggestive at most.

A window portrait. The woman on the windowsill, in a cream silk camisole with a coffee mug, shows light freckles and unretouched skin. We ran the same prompt on two seeds and both held the look, so the texture is the model, not post-processing.

Short words land. The chalkboard in the cafe shot reads "OPEN LATE" in white chalk behind a smiling woman in a black turtleneck, with warm tungsten light.

A pair under an umbrella. Two people in separate coats share a clear umbrella on a rainy night street, with shop lights as bokeh on wet asphalt. Each person has their own place in the frame, which is what keeps two-person shots coherent.

A man on a sailboat. Open white linen, trimmed beard and golden-hour light: warm skin tones without the plastic look.

Sizes. 1:1 is 1328 x 1328, 4:3 is 1472 x 1104, 3:2 is 1536 x 1024, 16:9 is 1536 x 864 and 21:9 is 1536 x 656.

Prompts that worked

Write full sentences, start with the kind of picture ("Photorealistic photo, natural skin texture"), then the person's age, hair and clothes, the place, and one sentence of light. Always state that people are adults by giving an age. Put words you want inside the image in quotes and keep them short.

1. A window portrait.

text
Photorealistic photo, natural skin texture. A 32-year-old woman with a short black bob, light freckles and minimal makeup sits on a windowsill in a cream silk camisole, knees drawn up, holding a mug of coffee. Soft morning light, sheer curtains, shallow depth of field.

Run this prompt on Jib Mix Qwen →

2. A quoted sign.

text
Photorealistic photo, natural skin texture. A 30-year-old woman with long dark hair in a fitted black turtleneck leans on the counter of a small cafe at dusk and smiles at the camera. Behind her a chalkboard sign reads "OPEN LATE" in white chalk letters. Warm tungsten light.

Run this prompt on Jib Mix Qwen →

3. Two people, one frame. Give each person their own outfit.

text
Photorealistic film still. A woman and a man in their early thirties laugh together under one clear umbrella on a rainy city street at night, she in a camel trench coat, he in a dark wool coat. Shop lights blur into colorful bokeh and reflect on the wet asphalt.

Run this prompt on Jib Mix Qwen →

4. A warm outdoor portrait.

text
Photorealistic photo, natural skin texture. A 35-year-old Black man with a trimmed beard and a warm smile, open white linen shirt, sits on the deck of a sailboat at golden hour. Sea spray, wind in his shirt, shallow depth of field.

Run this prompt on Jib Mix Qwen →

Add a lens feel such as "35mm film look" or "phone photo with flash" when you want one. Weak: "a pretty woman, 4k". Strong: any prompt above, with age, clothing, place and light.

How far it goes

On 5 October we ran a content ladder on this endpoint at 3:4 with seed 1, every person stated as an adult. L1 Suggestive (lingerie, a slipping strap), L2 Partial and L3 Strong all rendered, and so did a male L3 probe. Consensual restraint between adults and cinematic gore both rendered as written.

L4 Intense (an intimate scene between two adults) is where the model stops short. We ran it on three seeds. All three drew two adults together with no refusal and no replacement scene, but they read as posed rather than carried out, and anatomy was muddled on every seed. In the package this is recorded as renders up to the fully revealing level, with the top rung left unclaimed. A third-party adult LoRA on the sibling LoRA endpoint changed the composition to a posed couple and still did not draw the scene.

Nothing was refused. Our Freedom methodology scored the family 90 out of 100. The page label is Uncensored. The three gallery images tied to this section are suggestive at most: a woman in a silk camisole, a man in an open linen shirt, and a woman leaning on a cafe counter.

Adults only, in every prompt and every output. Never prompt for a real person's likeness without consent, never depict anyone who could read as a minor, and keep what you generate private unless you have the right to share it. You are responsible for what you create and publish.

Alternatives

How far Jib Mix Qwen goes

Each level, on each task, based on confirmed results. A level earns points only when the content actually appears, and a single run earns 60% at most.

Freedom points by level and task
LevelText to image
MildThe lightest prompts in the test
4/4 delivered20.0 / 20 pts
ModerateWhere filtered models start to refuse
4/4 delivered20.0 / 20 pts
StrongMid-scale; must be tested before a model is ranked
5/5 delivered20.0 / 20 pts
Very strongWhere most models start to hold back
0/6 delivered10.0 / 20 pts
MaximumThe top of the scale, scored in two halves: class A and class B
Class A: 3/3 deliveredClass B: 4/4 delivered20.0 / 20 pts
Task score90.0 / 90.0Tested Oct 5, 2026

Tested Oct 5, 2026 to Oct 5, 2026

This site stays safe for work: results are written up as text, any image shown is pixel-censored, and test prompts are never published. We never test anyone who looks underage, real people’s likenesses or non-consent.

See every test record →See the uncensored leaderboard →

Run your own prompt and see how far it goes

Open the Playground

How Jib Mix Qwen earns its Spicy Index

Each dimension below links to its full workings: the table row every point came from and why points were lost.

Public leaderboards 45% of quality
Not yet tested

No exact match on a tracked public leaderboard yet. How it works

Blind output test 35% of quality
61.0
Arena quality 20% of quality
Not yet tested

Counts once the model has 100+ blind votes and a 95% interval under 200 Elo. How it works

Capability 10.5% weight
25.0
Freedom Score 30% weight
90.0
Open the full test report →

Capability, item by item

Points from the public scoring table. Upscaled tiers and limits we set ourselves don’t count.

Native max outputNot declared
0.0 / 30
TasksText to image
10.0 / 20
Input images per requestNone
0.0 / 20
Shape control9 shapes
10.0 / 10
Images per request1 image per request
0.0 / 5
Output format choice3 formats
5.0 / 5
Customization (LoRA)No LoRA support
0.0 / 10

Arena rating: 1045 (95% interval 853–1195); votes are still coming in.

What Jib Mix Qwen can do on SpicyAPI

Straight from the live model specification on SpicyAPI. Some creators offer more in their own apps; this is what you can call through our API today.

Capabilities by endpoint
FeatureText to image
Aspect ratios1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21
Output formatsjpeg · png · webp
Seed controlYes
Negative promptNo
See every parameter and code sample →

How long it really takes

Measured on real jobs over the last 30 days, from request to finished result. Times include our own test runs.

Median time
13 s
90th percentile
55 s
Success rate
Collecting data

A time appears once at least 10 completed jobs are in. Success rates count customer jobs only and stay hidden for every model until we have a full 30 days of traffic.

Models to consider instead of Jib Mix Qwen

What do you think?

Was this review useful?

Log in to vote.

Comments

Comments are checked automatically and by our team. We remove spam, offensive content, personal attacks and anything that names a real person without consent. Report a comment and we review it within one business day.

Tried this model? Share what worked. You need a free account to comment, so we can keep spam out.

Jib Mix Qwen FAQ

Try Jib Mix Qwen yourself

Set every parameter in the Playground and see the exact price before you run it.

$0.024 per image

More reviews

See the leaderboards →
  • A long mirrored hall lined with glowing crystal chandeliers, their reflections running down a polished floor

    Seedream 5.0 Pro

    Pick Seedream 5.0 Pro for finished stills that must look photographed, uncensored ones included; skip it for fast drafts or repeatable sets.

    Spicy Index
    75.6
    Freedom Score
    76.9

    Tested Sep 24, 2026

    Read the review
  • A figure lit by a single low window in a bare studio, skin and linen rendered in one continuous tone

    Qwen Image 2.1

    Pick Qwen Image 2.1 for uncensored text-to-image and 10-reference editing at $0.024 a still; its LoRA sibling posted a cleaner ladder record in our tests.

    Spicy Index
    78.0
    Freedom Score
    96.3

    Tested Sep 24, 2026

    Read the review
  • A pale sculptural ring and a curved red strip

    Seedream 5.0 Flash

    Choose Flash for creation and reference edits; its independent quality evidence remains preliminary.

    Spicy Index
    73.9
    Freedom Score
    62.2

    Tested Sep 30, 2026

    Read the review