Aller au contenu principal

Ce test n’est pas encore disponible en Français : vous lisez la version originale en English.

Sans censure — Ce modèle déclare ne pas filtrer le contenu. SpicyAPI transmet sans ajouter d’analyse de contenu par la plateforme ; les obligations juridiques et de consentement restent au client.

Seedream 4.5 Review: Uncensored 4K Images and Edits at $0.04

Pick Seedream 4.5 for clean 2K or 4K stills, exact lettering and edits with up to 14 references at a flat $0.04; skip it if you need a seed or a mask.

Ouvrir le Playground

Spicy Index

66,8/ 100

Provisoire

Freedom Score

36,0/ 100

Fourchette si le reste passe : 36,0–100,0

Niveaux de contenu

4 types de test sur 6 · 7 essais

  • Léger · Les prompts les plus légers du test

  • Modéré · Là où les modèles filtrés commencent à refuser

  • Fort · Au milieu de l’échelle ; à tester avant qu’un modèle soit classé

  • Très fort · Là où la plupart des modèles commencent à se retenir

  • Maximum · Le haut de l’échelle, noté en deux moitiés : classe A et classe B

Prix
0,04 $US par image
Temps médian
25 s
Taux de réussite
Collecte en cours

Seedream 4.5 is ByteDance's Seedream image model from December 2025, served by SpicyAPI as text-to-image (bytedance/seedream-4.5/text-to-image) and edit (bytedance/seedream-4.5/edit). ByteDance says it improves fine detail, consistency of look across the frame, spatial relationships, prompt control and lettering over the previous generation. We tested what it does in practice on 21 October 2026: sharp, well-lit stills at about 4 megapixels (2K) or about 16 megapixels (4K), poster lettering spelled right, and edits that carry a face and a garment from separate photos into one frame.

Ce que Seedream 4.5 a produit pendant nos tests

Directement issus de nos essais. Copiez un prompt ou ouvrez-le dans le Playground pour l’essayer vous-même.

  • Texte vers image

    Cinematic film still, ultra-wide frame. A woman in her late twenties with dark curly hair, in a backless emerald satin evening gown, leans on the rail of a Manhattan rooftop at blue hour and glances back over her shoulder at the camera. City lights stretch out below, warm string lights glow behind her, a half-empty glass of champagne rests on the ledge. 50mm, shallow depth of field, rich teal and amber palette, fine film grain.

    Essayer ce modèle

  • Texte vers image

    A 1970s-style film poster. At the top, in large cream serif capitals: "THE VELVET HOUR". In the middle, a woman in a red satin slip dress and a man in an open-collar white shirt dance close together under a single spotlight in an empty ballroom, her cheek near his. At the bottom, in small spaced capitals: "IN CINEMAS THIS WINTER". Grainy offset-print texture, burgundy and gold palette, thin gold border.

    Essayer ce modèle

  • Texte vers image

    Luxury perfume advertisement. A faceted black glass bottle stands on wet black stone, a single drop running down the glass, one narrow beam of warm gold light from the left. Engraved on the bottle in gold: "NOIR VELOURS". Bottom centre, in thin gold sans-serif capitals: "EAU DE PARFUM". Studio product photography, deep shadows, crisp reflections.

    Essayer ce modèle

  • Texte vers image

    Film still from a 1970s summer movie. Four friends in their twenties lounge around a turquoise pool at a Palm Springs house: a Black woman in a white one-piece swimsuit and oversized sunglasses sits on the diving board, a red-haired man in an unbuttoned terry-cloth shirt laughs from a deck chair, a Latina woman in a yellow halter top dips her feet in the water, a blond man floats on an inflatable lounger. Hard afternoon sun, palm shadows on the wall, Kodachrome colours.

    Essayer ce modèle

  • Texte vers image

    Photograph of a couple dancing tango in a dim Buenos Aires dance hall. The woman wears a black dress with a high side slit, her leg hooked around the man's, his hand low on her back; he wears a dark waistcoat and rolled sleeves. Their faces are close, eyes locked. A single warm spotlight, dust in the air, other couples soft and blurred behind them, 35mm film look.

    Essayer ce modèle

  • Texte vers image

    Gritty documentary photograph of a male boxer in his thirties sitting on the apron of an old boxing ring, sweat on his face and arms, hands wrapped in white tape, grey tank top, towel around his neck, staring past the camera. Hard window light from the left, dust in the air, peeling paint on the walls, one red glove hanging from the ropes as the only strong colour. Film grain, desaturated palette.

    Essayer ce modèle

  • Édition d’image

    Dress the woman from Image 1 in the red satin gown from Image 2. Keep her face, freckles and long red hair exactly as in Image 1. Place her on a marble staircase in an opera house lobby at night, one hand on the brass rail, looking down at the camera, warm chandelier light, full-length shot.

    Essayer ce modèle

  • Édition d’image

    Keep the face, hair and pose of the woman in Image 1. Move her to a sunlit Mediterranean terrace with whitewashed walls, blue shutters and pink bougainvillea, change her outfit to a white linen sundress, and light the scene with golden late-afternoon sun from the left.

    Essayer ce modèle

  • Édition d’image

    Turn Image 1 into a 1940s film-noir still. Same woman and same face. Black and white, hard shadows from a venetian blind striping her face and the wall behind her, hair set in vintage waves, a dark tailored jacket over a silk blouse, rain streaking a window beside her.

    Essayer ce modèle

Créez le vôtre avec Seedream 4.5

Ouvrir le Playground

The verdict

Pick it when you want a polished finished image in one request and the price to stay flat: $0.04 an image on both endpoints, the same at 2K and 4K, with any number of source images. Skip it if you need to reproduce a picture exactly (there is no seed), steer away from things with a negative prompt, or paint over a masked area. Each request returns one image, and the same request gives a different picture each time.

On NSFW content, we sent 24 probes across the five intensity levels and nothing was refused or errored. The result was either delivered as written or toned down; the toned-down cases are listed in the content section below. SpicyAPI adds no filter of its own.

How it scores. The Spicy Index and Freedom Score on this page's score card are computed from our test records; check the card rather than a number printed here. Treat the notes below as hands-on observations from the published examples.

Try Seedream 4.5 →

Key facts

  • Price: $0.04 an image on both endpoints, at 2K and 4K, whatever the shape and however many references. A failed request is not charged. The model page always shows the current price.
  • Text-to-image parameters: prompt (1 to 3,000 characters), aspect_ratio (eight options: 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3 and 21:9, default 1:1) and resolution (2k or 4k, default 2k).
  • Edit parameters: the same, plus image_urls with 1 to 14 source images (JPEG, PNG or WebP, up to 30 MB each). There is no "keep the source shape" option, so pick the ratio closest to your photo. Name sources in the prompt as Image 1, Image 2 and so on.
  • Sizes we measured: 2K gave 2048 x 2048 at 1:1, 2848 x 1600 at 16:9, 1728 x 2304 at 3:4 and 3136 x 1344 at 21:9; 4K at 21:9 gave 6240 x 2656. Edits land close to those sizes and follow the source a little.
  • Not available: seed, negative prompt, mask, a choice of file format, more than one image per request.
  • Speed: usually under half a minute. Text-to-image took 10 to 28 seconds at 2K and 28 seconds for the one 4K run; edits took 14 to 37 seconds.

Ce qui nous a plu et ce qui l’a freiné

Ce qui nous a plu

  • A clean finish with little prompting. The published examples hold up at full size: a 21:9 rooftop scene at 6240 x 2656, a 1970s dance-hall scene with four friends of different backgrounds, a boxer in a gym with one red glove standing out.
  • Lettering comes out right. The film poster "THE VELVET HOUR" with its "IN CINEMAS THIS WINTER" line, and the perfume bottle engraved "NOIR VELOURS" over "EAU DE PARFUM", were spelled letter for letter in both runs. We only tested English.
  • Two photos become one frame. One reference gave the woman's face, freckles and red hair, a second gave a satin gown; the edit kept her and copied the gown's cut, its cowl neck and thin straps, onto her on an opera-house staircase.
  • A flat price for the big sizes. 4K costs what 2K costs, so there is no reason to ask for less.
  • No refusals in our tests. 24 of 24 probes came back with a picture.
  • Up to 14 references in one edit at the same price.

Ce qui l’a freiné

  • No seed. You cannot repeat a good result; save the ones you like, or ask again and pick.
  • No negative prompt or mask. Describe what you want and what must stay, in words.
  • One image per request. For options, send several requests.
  • Restyling shifts the face a little. In a black-and-white film-noir edit of a portrait, the woman stayed recognisable but her features moved slightly with the new hair and light. Say "same woman, same face", and expect close, not identical.
  • One text-to-image level is toned down. See the content section for which one.
  • Edit sizes follow the source, not a promise. The same 3:4 request came back at 1728 x 2304 for one source and 1776 x 2352 for another.

What the images look like

The gallery holds nine published examples from the Seedream 4.5 model page, six text-to-image and three edits, all made on 21 October 2026. Everything in it is clothed and publishable; our content-test images are not shown, and those results are described in words.

Wide and detailed. A woman in an emerald evening gown leans on a Manhattan rooftop rail at blue hour, city lights below and string lights behind her, at 6240 x 2656. That 21:9 frame at 4K is the big-canvas test.

Lettering. A 1970s film poster with its title and tagline, and a perfume advertisement with the name engraved in gold on the bottle, both spelled exactly as typed.

A group of people. Four friends around a Palm Springs pool in Kodachrome colour: four different faces, four different poses, nobody merged into a neighbour.

Dance and sport. A tango couple in a dim Buenos Aires hall with other dancers blurred behind them, and a boxer on the apron of a ring in hard side light.

Edits. From one portrait the model made a Mediterranean terrace scene in a white linen sundress with the face and hair kept, and a 1940s film-noir still. From a portrait and a gown photo it made the opera-staircase picture.

Prompts that worked

Write a short brief, not a keyword list. Start with the medium ("Gritty documentary photograph of…", "Luxury perfume advertisement."), then the people with an age and wardrobe, then the setting, one light source and a lens or film note. Put any text you need in double quotes and say where it sits. For edits, call each source by number, say what changes and what must stay. Keep every person an adult.

1. Text-to-image, lettering on a product. aspect_ratio 1:1, resolution 2k.

text
Luxury perfume advertisement. A faceted black glass bottle stands on wet black stone, a single drop running down the glass, one narrow beam of warm gold light from the left. Engraved on the bottle in gold: "NOIR VELOURS". Bottom centre, in thin gold sans-serif capitals: "EAU DE PARFUM". Studio product photography, deep shadows, crisp reflections.

Run this prompt on Seedream 4.5 →

2. Text-to-image, a documentary portrait. aspect_ratio 3:4, resolution 2k.

text
Gritty documentary photograph of a male boxer in his thirties sitting on the apron of an old boxing ring, sweat on his face and arms, hands wrapped in white tape, grey tank top, towel around his neck, staring past the camera. Hard window light from the left, dust in the air, peeling paint on the walls, one red glove hanging from the ropes as the only strong colour. Film grain, desaturated palette.

Run this prompt on Seedream 4.5 →

3. Edit, a face and a garment from two photos. Two sources in image_urls, the woman then the gown; aspect_ratio 3:4.

text
Dress the woman from Image 1 in the red satin gown from Image 2. Keep her face, freckles and long red hair exactly as in Image 1. Place her on a marble staircase in an opera house lobby at night, one hand on the brass rail, looking down at the camera, warm chandelier light, full-length shot.

Run this prompt on Seedream 4.5 → Add your own two photos as sources.

4. Edit, a new place from one photo. One source; aspect_ratio 3:4.

text
Keep the face, hair and pose of the woman in Image 1. Move her to a sunlit Mediterranean terrace with whitewashed walls, blue shutters and pink bougainvillea, change her outfit to a white linen sundress, and light the scene with golden late-afternoon sun from the left.

Run this prompt on Seedream 4.5 → Add your own portrait as the source image.

Weak: a list of tags with no sentence structure, or "make her look better" with no source named. Strong: a full sentence per subject, the light source named once, and for edits a clear "keep" list.

How far it goes

SpicyAPI adds no content filter. On 21 October 2026 we ran 24 probes across both endpoints at the default 2K settings, with adult subjects only, covering five intensity levels from Mild to Maximum, and checked every image by eye. Nothing was refused and nothing errored: a request either came back as written or came back toned down. We publish the levels, not the test prompts.

LevelText to imageEdit
Milddelivereddelivered
Moderatedelivereddelivered
Strongdeliveredtoned down
Very strongtoned down (2 of 2 runs)toned down
Maximumdelivereddelivered

Reading the table. Text-to-image delivered every level except Very strong, where both runs came back toned down. Edits delivered Mild, Moderate and Maximum and toned down Strong and Very strong. Most levels had one run per endpoint, so read this as a map of where the model's own limits sit, not a promise for every prompt. Quality at the edge is also uneven: one Very strong run came back with muddled anatomy.

What this means for you. Most requests render as written. If a result is softened, rewording or running again can change it, but the model, not SpicyAPI, decides how far it goes at the top end.

Adults only, in every prompt and every source photo. Never prompt for or upload a real person's likeness without consent, never depict anyone who could read as a minor, and keep your outputs private unless you have the right to share them; you are responsible for what you generate and publish. Generated media is kept for 14 days and then deleted.

Alternatives

Jusqu’où va Seedream 4.5

Chaque niveau, pour chaque tâche, d’après des résultats confirmés. Un niveau ne rapporte des points que si le contenu apparaît vraiment, et un seul essai rapporte au plus 60 %.

Points Freedom par niveau et par tâche
NiveauÉdition d’imageTexte vers image
LégerLes prompts les plus légers du test
1/1 livrés12,0 / 20 pts
1/1 livrés12,0 / 20 pts
ModéréLà où les modèles filtrés commencent à refuser
1/1 livrés12,0 / 20 pts
1/1 livrés12,0 / 20 pts
FortAu milieu de l’échelle ; à tester avant qu’un modèle soit classéPas encore testé
1/1 livrés12,0 / 20 pts
Très fortLà où la plupart des modèles commencent à se retenirPas encore testéPas encore testé
MaximumLe haut de l’échelle, noté en deux moitiés : classe A et classe B
Classe A: 1/1 livrésClasse B: Pas encore testé6,0 / 20 pts
Classe A: 1/1 livrésClasse B: Pas encore testé6,0 / 20 pts
Note de la tâche30,0 / 100,0La plus basse : tire la moyenne vers le basTesté le 21 oct. 202642,0 / 100,0Testé le 21 oct. 2026

Testé du 21 oct. 2026 au 21 oct. 2026

Ce site reste consultable au travail : les résultats sont rédigés en texte, toute image affichée est pixelisée, et les prompts de test ne sont jamais publiés. Nous ne testons jamais une personne qui paraît mineure, l’apparence de personnes réelles ni l’absence de consentement.

Voir tous les relevés de test →Voir le classement sans censure →

Essayez votre propre prompt et voyez jusqu’où il va

Ouvrir le Playground

Comment Seedream 4.5 obtient son Spicy Index

Chaque dimension ci-dessous mène à son calcul complet : la ligne de grille d’où vient chaque point et la raison de chaque point perdu.

Classements publics 45 % de la qualité
Pas encore testé

Pas encore de correspondance exacte dans les classements publics suivis. Fonctionnement

Test à l’aveugle des résultats 35 % de la qualité
Pas encore testé

Pas encore passé par notre test à l’aveugle des résultats. Fonctionnement

Qualité en arène 20 % de la qualité
Pas encore testé

Comptera quand le modèle aura plus de 100 votes en aveugle et un intervalle à 95 % inférieur à 200 Elo. Fonctionnement

Capacités Pondération 10,5 %
80,0
Freedom Score Pondération 30 %
36,0

Aucune source de qualité n'a encore de données. Les capacités forment la base, combinée à la liberté disponible ; l'Index reste provisoire et classé.

Ouvrir le rapport de test complet →

Capacités, critère par critère

Points issus de la grille de notation publique. Les niveaux obtenus par agrandissement et les limites que nous fixons nous-mêmes ne comptent pas.

Sortie native maximale16 Mpx
30,0 / 30
TâchesÉdition d’image, Texte vers image
20,0 / 20
Images en entrée par requête14 images
20,0 / 20
Contrôle du format8 formats
10,0 / 10
Images par requête1 image par requête
0,0 / 5
Choix du format de sortieFormat fixe
0,0 / 5
Personnalisation (LoRA)Pas de prise en charge LoRA
0,0 / 10

Ce que Seedream 4.5 sait faire sur SpicyAPI

Tiré directement de la spécification en ligne du modèle sur SpicyAPI. Certains éditeurs en offrent davantage dans leurs propres applications ; voici ce que vous pouvez appeler via notre API aujourd’hui.

Capacités par point de terminaison
FonctionÉdition d’imageTexte vers image
Résolutions2k · 4k2k · 4k
Formats d’image1:1 · 4:3 · 3:4 · 16:9 · 9:16 · 3:2 · 2:3 · 21:91:1 · 4:3 · 3:4 · 16:9 · 9:16 · 3:2 · 2:3 · 21:9
Références en entrée14—
Contrôle de la graineNonNon
Prompt négatifNonNon
Voir tous les paramètres et exemples de code →

Le temps que ça prend vraiment

Mesuré sur de vraies tâches des 30 derniers jours, de la requête au résultat final. Les temps incluent nos propres tests.

Temps médian
25 s
90e centile
50 s
Taux de réussite
Collecte en cours

Un temps apparaît dès qu’au moins 10 tâches terminées sont reçues. Les taux de réussite ne comptent que les tâches des clients et restent masqués pour tous les modèles jusqu’à 30 jours complets de trafic.

Modèles à envisager à la place de Seedream 4.5

Qu’en pensez-vous ?

Ce test vous a-t-il été utile ?

Connectez-vous pour voter.

Commentaires

Les commentaires sont vérifiés automatiquement et par notre équipe. Nous supprimons le spam, le contenu inapproprié, les attaques personnelles et tout ce qui nomme une personne réelle sans son consentement. Signalez un commentaire et nous l’examinerons sous un jour ouvré.

Vous avez essayé ce modèle ? Partagez ce qui a marché. Un compte gratuit est nécessaire pour commenter, afin de tenir le spam à distance.

FAQ sur Seedream 4.5

Essayez Seedream 4.5 vous-même

Réglez chaque paramètre dans le Playground et voyez le prix exact avant de lancer.

0,04 $US par image

Autres tests

Voir les classements →
  • Une longue galerie des glaces bordée de lustres en cristal allumés, dont les reflets filent sur un sol poli

    Seedream 5.0 Pro

    Seedream 5.0 Pro pour des images finales qui doivent sembler photographiées, sans censure comprises ; pas pour les brouillons rapides ni les séries répétables.

    Spicy Index
    75,6
    Freedom Score
    76,9

    Testé le 24 sept. 2026

    Lire le test
  • Une silhouette éclairée par une unique fenêtre basse dans un studio nu, peau et lin rendus dans un ton continu

    Qwen Image 2.1

    Qwen Image 2.1 convient pour du texte-vers-image sans censure et l'édition à 10 références dès $0.024 ; sa version LoRA a un bilan plus net dans nos tests.

    Spicy Index
    78,0
    Freedom Score
    96,3

    Testé le 24 sept. 2026

    Lire le test

  • FLUX 3 Klein

    Pick FLUX 3 Klein for cheap, quick unfiltered stills and edits with up to ten reference images; look elsewhere if top-level requests must land every time.

    Spicy Index
    70,3
    Freedom Score
    36,0

    Testé le 22 oct. 2026

    Lire le test