Tools using artificial intelligence are being developed at a rapid pace. One of these tools is the text-to-image generator DALL·E 2 which has been developed by OPEN-AI and is meant to generate images solely through text input. One of the problems with tools like these is that they are not as good at generating material as AI generators for speech or text are. As DALL·E 2 has been made available to be used for commercial purposes there is a need to evaluate whether the tool is good enough to be used for that purpose. The study was conducted through 3 focus groups with a total of 15 participants. The participants were 20 to 25 years old. During the focus groups, already generated images were discussed and they were allowed to test use of the tool themselves. The theoretical framework Technology Acceptance Model 2(TAM-2) was used to analyze the qualitative data according to its already established determining factors. The result of the study presents area of usage as a new extending factor for the perceived usefulness when using TAM-2 in a qualitative study. The conclusion is drawn that visual material created by DALL·E is not seen as accepted for use in a commercial purpose but its application within certain areas of usage could raise the perceived usefulness, and thereby acceptance. / Verktyg som bygger på artificiell intelligens utvecklas i snabb takt. Ett av dessa verktyg är text-till-bild-generatorn DALL·E 2 som utvecklats av OPEN-AI och är menat att generera bilder utifrån text. Ett problem med verktyg som DALL-E 2 är att de inte är lika bra på att skapa visuellt material som generatorer är för ljud eller text. I och med att verktygen börjat göras tillgängliga kommersiellt så finns det ett behov att undersöka huruvida verktygen är tillräckligt bra för att kunna användas till det. Studien genomfördes med tre fokusgrupper med totalt 15 deltagare. Deltagarna hade en ålder mellan 20 och 25 och man diskuterade acceptans till tidigare genererat bildmaterial samt upplevelsen av att använda verktyget själva. Technology Acceptance Model 2 (TAM-2) användes som teoretiskt ramverk för analys av den kvalitativa datan och för påverkande faktorer. Resultatet presenterar sammanhang som en ny påverkande faktor för den uppfattade användbarheten i användningen av TAM-2 i kvalitativa studier. Slutsatsen dras att bildmaterial skapat av DALL·E 2 inte anses accepterat för användning i ett kommersiellt sammanhang men tillämpning i specifika sammanhang skulle kunna höja den uppfattade användbarheten och därmed acceptansen.

No description available.

No description available.

"Image and Text" focuses on the consequences of multi-media interaction on the concept of a work's meaning(s) in three distinct publishing trends in nineteenth-century Britain: graphic satire, the literary annuals, and book illustration. The graphic satire of engravers James Gillray and George Cruikshank is replete with textual components that rely on the interaction of media for the overall satirical impact. Literary annuals combine engravings with the ekphrastic poetry of writers including William Wordsworth, Samuel Taylor Coleridge, Robert Southey, and Letitia Elizabeth Landon. Book illustrations provided writers Sir Walter Scott and Alfred, Lord Tennyson a means to recycle previously published works as "new" texts; the engravings promote an illusion of textual originality and reality by imparting visual meanings onto the text. In turn, the close proximity of text to image changes visual meanings by making the images susceptible to textual meanings. Many of the theoretical implications resulting from the pairing of media resound in modern film adaptations, which often provide commentary about nineteenth-century visual culture and the self-reflexivity of media. The critical heritage that has responded to the pairing of media in nineteenth-century print culture often expresses uneasiness with the relationship between text and mechanically produced images, and this uneasiness has often resulted in the treatment of text and image as separate components of multi-media works. "Image and Text" recovers the dialogue between media in nineteenth-century print forms often overlooked in critical commentary that favors the study of an elusive and sometimes fictional concept of an original work; each chapter acknowledges the collaborative nature of the production of multi-media works and their ability to promote textual newness, originality (or the illusion of originality), and (un)reality. Multi-media works challenge critical conventions regarding artistic and authorial originality, and they enter into battles over fidelity of meaning. By recognizing multi-media works as part of a diverse genre it becomes possible to expand critical dialogue about such works past fidelity studies. Text and image cannot faithfully represent the other; what they can do is engage in dialogue: with each other, with their historical and cultural moments, and with their successors and predecessors.

Cette thèse consiste en une recherche sur la représentation du paysage dans les arts poétique et visuel, à partir d’un éclairage réciproque entre cultures occidentale (principalement française et antique) et chinoise. Notre recherche est inspirée par la définition canonique du paysage: le paysage est une portion de l'espace terrestre, représentée ou observée à l'horizontale comme à la verticale par un observateur. En conséquence, pour les chercheurs de la littérature moderne, c’est le surgissement de la notion de « sujet » qui engendre la notion du paysage dans son sens étymologique. En revanche, dans la poésie chinoise ancienne dont la syntaxe est nominale, l’être, comme prédicat dominant qui structure la vision du sujet vis-à-vis du paysage, est souvent absent. Le langage chinois reflète une perspective non-anthropocentrique du paysage en Chine ancienne. Une deuxième étude significative conduit à la révision de la conception canonique du paysage: Celle de l’art visuel et poétique ancien, qui permet d’écrire une préhistoire du paysage (les éléments naturels) et de proposer une théorie de l’émergence du paysage dans l’Antiquité. Cette tentative proposant la naissance du paysage dans l’Antiquité se distingue dès lors de celle qui la fait naître à la Renaissance. Je m’efforce d’esquiver « le grand récit » proclamant une vérité universellement valable, pour préconiser « les petits récits » qui précisent « les représentations localisées du domaine restreint ». J’ai choisi un certain nombre de thèmes fondamentaux concernant le paysage - le sublime, la Stimmung, les ruines et le vide -, que j’interroge sur des problématiques comme celle du lien entre sujet et objet, la conscience de l’histoire et le lieu de mémoire, etc. / This dissertation focuses on the representation of landscape in poetry and visual arts, with the reciprocal illumination of Western (mainly French and Antiquity) and Chinese culture. This research is inspired by the canonical definition of landscape that the landscape is a portion of space represented or observed horizontally or vertically by an observer. Accordingly, for researchers of modern literature, the emergence of the concept of "subject" generates the notion of landscape in the etymological sense. However, in ancient China, “be” as a predicate is often absent in poetry, especially in the nominal syntax. The Chinese language reflects a non-anthropocentric perspective of landscape, about which Stimmung and Qingjing (the emotion-landscape) deconstruct the notion of landscape structured by the “subject“. The Approach to the revision of the canonical landscape concept is to introduce the ancient visual art and poetry so as to write a prehistory as well as a history of landscape (natural elements) and to propose about the emergence of the landscape in Antiquity, even if I can not find a term corresponding exactly to the modern landscape. This attempt, proposing the birth of the landscape in ancient times, is different from the well-known claim that the landscape was born in the Renaissance. In this research, I try to dodge the "grand narrative" proclaiming a universally valid truth, but to advocate "small stories" that specify "localized representations of the restricted area." Thus, I chose four fundamental themes such as sublime, Stimmung, ruins and vide, so as to discuss the relationship between subject and object, consciousness of history and place of memory, etc.

Att kommunicera rummets varierande funktion genom 3D-visualiseringar är ett examensarbete i informationsdesign med inriktning rumslig gestaltning. Uppdraget kommer från Husmuttern AB som arbetar med huskoncept som sedan ska leda till produktion av modulhus. Syftet med arbetet har varit att studera hur en 3D-modell bör utformas för att kommunicera ett rums varierande funktion. Detta för att veta hur jag ska visualisera en undervisningssal i ett modulhus. För att arbeta fram en 3D-modell som uppfyller dessa krav krävs det att studera kommunikation mellan parter, bildens egenskaper, rummets form och färg, detta med stöd i litteratur, forskning och användartester. Därefter kunde en modell arbetas fram som kunde kommunicera en undervisningssal i ett modulhus. Genom användartesterna visade det sig att det är bra med en modell som fokuserar på modulhusets grund men också att ha med inredning för att visa funktionen. Det resulterade i en modell som innehöll husgrunden på en halva och realistisk inredning på den andra halvan men i samma modell. Genom litteratur och tidigare forskning blev resultatet för visualiseringar att det är ofta som 3D-modeller används. I utformningen bör detaljer uteslutas och verklighetstrogna vyer undvikas. Fokus bör ligga på det väsentliga då det annars blir för mycket att ta in för betraktaren och budskapet går förlorat, samt att verklighetstrogna skisser upplevs som färdigutvecklade. Det resulterade i en skissartad modell med avskalad inredning för att visa rummets funktion. / Att kommunicera rummets varierande funktion genom 3D-visualiseringar is a thesis in information design with orientation in spatial design. The assignment comes from the company Husmuttern AB who work with house concept that will lead to production of module housing. The purpose has been to study how a 3D- visualisation should be formed to communicate rooms varying functions. All this so that I will know how to visualize a classroom in a module housing. To be able to come up with a 3D-model that have this quality it was requires to study communication between two parties, properties of the image, shape and color of the room, with the help of literature, previous research and user tests. Then it was possible to come up with a model that could communicate a classroom constructed in module. Through the user tests it was shown to be preferable with a model that focuses on the basic units of the module housing but that also has some realistic decor to show some function. All this resulted in a model which includes the basic units of the module on one half and realistic décor on the other half in the same model. Thanks to literature and previous research the result for visualization was that it is common to use 3D-modells. In the modeling details and realistic views should be avoid. The focus should be on the essential or it will be too much for the viewer to take in and the message gets lost, but also that to realistic models were considered to be fully complete. All this resulted in a sketchy model with a small amount of décor to show the rooms function

Cette thèse a pour origine le constat de la non prise en charge des ouvrages se caractérisant par leur seule iconicité scripturale en histoire du livre et de l’édition ainsi que de l’absence de définition d’une catégorie les regroupant aussi bien dans cette discipline qu’en littérature, histoire du graphisme, sémiotique ou histoire de l’art. Notre première hypothèse est que cette catégorie correspond au « livre graphique ». C’est par les littéraires, soit dans une approche par auteur, soit à travers l’étude de la poésie visuelle, que certains de ses ouvrages ont été abordés, avec les lacunes inhérentes à la discipline. Il nous a donc semblé essentiel d’adopter un point de vue pluridisciplinaire, en insistant sur l’histoire des techniques. Cette exigence nous a permis de distinguer au sein du « livre graphique », le livre (typo)graphique, au côté du livre (calli)graphique, (dactylo)graphique, etc., et de choisir de nous consacrer à la première sous-catégorie, afin de défendre notre deuxième hypothèse : le sursaut de la création typographique, réaction à son industrialisation de la fin du XIXe siècle jusqu’aux années 1980. Aux incunabula typographiae répondrait donc cinq siècles plus tard un livre(typo)graphique comme « ultima typographiae ».La première partie consiste en une identification théorique du livre (typo)graphique. Une enquête historiographique analyse les barrières épistémologiques à la considération critique de notre objet tout en dégageant nos outils conceptuels : les thèses de Johanna Drucker et d’Anne-Marie Christin. Suivent une histoire du livre (typo)graphique puis la définition d’un ensemble de traits génériques et typologiques.La deuxième partie consiste dans la recherche des producteurs de livres (typo)graphiques par le prisme des auteurs. Le premier chapitre se fonde sur l’histoire littéraire, et procède donc par mouvement. Cette méthode présente toutefois deux écueils. D’abord, la spécificité de l’objet d’étude - le livre et non pas le texte graphique - implique une approche technique mais aussi génétique sur le plan éditorial que favoriserait plutôt un biais par éditeur.D’autre part, il ressort qu’un certain nombre d’auteurs de livres (typo)graphiques n’ont paradoxalement pas été retenus par ce premier tamis. Ceci nous permet d’énoncer deux nouvelles hypothèses. Premièrement, le livre(typo)graphique semble aussi caractéristique d’auteurs impliqués dans le discours sur l’art et l’évolution de l’appropriation de ce dernier par les poètes, une des causes du développement de notre objet. Il s’agit donc dans le deuxième chapitre de mettre en évidence le fil rouge reliant les productions de Claudel, Segalen, du Bouchet et Tardieu pour conclure au caractère d’« appropriation » littéraire de procédés picturaux de leurs livres (typo)graphiques. Deuxièmement, nous proposons une équivalence entre le livre(typo)graphique de ces auteurs et la « peinture lettrée », en nous fondant sur leurs textes critiques et transpositions d’art et sur la dernière thèse d’A.-M. Christin.Au terme de la deuxième partie, il ressort que la grande majorité des livres (typo)graphiques identifiés n’a pas été embrassée. La troisième partie consiste dans un balayage par le biais des éditeurs. Un résultat beaucoup plus fructueux permet de proposer une cinquième hypothèse : le livre (typo)graphique est principalement un livre d’éditeur.Le premier chapitre met en avant cinq évolutions de ce producteur de 1890 aux années 1980. Dans le dernier chapitre, nous nous penchons sur la production du « poète-typographe ». On établira un lien de causalité entre la maîtrise totale de la chaine de production de cet ouvrier-homme de lettre, et le fait qu’il soit le plus important contributeur de livres (typo)graphiques.Parvenue à son terme, cette thèse vise à constituer une contre-histoire du livre illustré ou un complément à celle du livre de création. / This thesis was formulated as an investigation into the lake of works treating of iconic scripturality in trough the history of book and publishing, and also the absence of any definition of the category to regroup them equally within this discipline as in literature, history of graphism, semiotic, history of art. Our initial hypothesis is that this category relates to the “graphic book”. It is trough specialist in literature, either in an approach by writer or passing through a close study of visual poetry, that certain of this works have been treated, with lacunae common to the discipline. In order to usefully complete the research work, it would seem essential to take on board a pluridisciplinary approach, emphasizing the technical history. These criteria allowed us to differentiate within the domain of the graphic book, the (typo)graphic book, around the (calli)graphic, (dactyl)graphic, etc., and to elect to focus upon the first subcategory, so as to justify our second hypothesis, that of a convulsion, in reaction to the meccanization of this industry at the end of the nineteen century through the decade of 1980’s. The incunabula typographiae would find its response five centuries later in the (typo)graphic book as ultima typographiae.The first part consists of a theoretical identification of the (typo)graphic book. An historiographical investigation would analyses epistemological barriers of the critical treatment of our object whilst bringing to light our conceptual tools: the thesis of Johanna Drucker and Anne-Marie Christin. Subsequently, establishing an history of (typo)graphic book and then, the definition of a group of generic traits and typologies.The second section is made up of a research into the producers of (typo)graphic books, as seen through the prism of the authors. The first chapter is based upon history of literature and thus proceeds by literary movement. Bearing in mind, this method is prey to tween dangers. First of all, the strictly specific nature of the study, the graphic book, but not text, implies a technical approach but also genetical in the editorial sense which would rather favour from an editor’s angle. Furthermore, it appears that a certain number of authors of (typo)graphic books, quiet paradoxically were not accounted for in this first selection. So, this allows us to articulate two new hypothesis. Firstly the (typo)graphic book seems also to be typified by authors involved in a discourse around art and the changing nature of the appropriation of the later by the poets, in itself one of the causes of the development of our object. Therefore, in the second chapter it would be a matter of highlighting the common thread uniting the productions of Claudel, Segalen, du Bouchet and Tardieu to conclude with the form of literary appropriation of pictorial processes of the (typo)graphic books. Secondly, we shall propose an equivalence between their (typo)graphic books and the literate painting, basing ourselves upon their critical texts and transposition of art and upon the last thesis of A.-M. Christin. At the clothe of the second section, one is still faced by the same difficulties that the great majority of identified typographical books hasn’t being catalogued.The third part would comprise of an overview from the publishers’ perspective. A much more productive result will allow us to formulate our fifth hypothesis: the (typo)graphic book is above all a publisher’s book. The first chapter will concentrate upon five evolutions of this producer. In the last chapter, we shall examine more specifically the production of the “typographic poet”. We shall establish a causal link between the total mastery of the production chain of this worker man of letters and the fact he became the most important contributor of (typo)graphic book.Reaching its conclusion, the thesis seeks to constitute, a counter-history of the illustrated book or a complement of that of the creative book.

No description available.

Language-based fashion image editing has promising applications in design, sustainability, and art. However, it is considered a challenging problem in computer vision and graphics. The diversity of human poses and the complexity of clothing shapes and textures make the editing problem difficult. Inspired by recent progress in editing face images through manipulating latent representations, such as StyleCLIP and HairCLIP, we apply those methods in editing the images of full-body humans in fashion datasets and evaluate their effectiveness. First, we assess different methodologies to find a latent representation of an image via Generative Adversarial Network (GAN) inversion; then, we apply three image manipulation schemes. Thus, a pre-trained e4e encoder is initially utilized for the inversion process, while the results are compared to a more accurate method, Pivotal Tuning Inversion (PTI). Next, we employ an optimization scheme that uses the Contrastive Language Image Pre-training (CLIP) model to guide the latent representation of an image in the direction of attributes described in the input text. We address the problem of the accuracy and speed of the process by incorporating a mapper network. Finally, we propose an optimized mapper called Text-Driven Garment Editing Mapper (TD-GEM) to achieve high-quality image editing in a disentangled way. Our empirical results show that the proposed method can edit fashion items for changing color and sleeve length. / Språkbaserad bildredigering inom mode har lovande tillämpningar inom design, hållbarhet och konst. Det betraktas dock som ett utmanande problem inom datorseende och grafik. Mångfalden och variationen av mänskliga poser och komplexiteten i klädform och texturer gör redigeringsproblemet svårt. Inspirerade av den senaste utvecklingen inom redigering av ansiktsbilder genom manipulation av latenta representationer, såsom StyleCLIP och HairCLIP, tillämpar vi dessa metoder för att redigera bilderna av fullständiga mänskliga kroppar i mode-dataset och utvärderar deras effektivitet. Först jämför vi olika metoder för att hitta en latent representation av en bild via så kallade Generative Adversarial Network (GAN) inversion; sedan tillämpar vi tre bildmanipulationsscheman. En förtränad (eng: pre-trained) e4e-encoder model används först för inversionsprocessen, medan resultaten jämförs med en mer exakt metod, Pivotal Tuning Inversion (PTI). Därefter använder vi en optimeringmetod som använder Contrastive Language Image Pre-training (CLIP) -modell för att vägleda den latenta representationen av en bild i riktning mot attribut som beskrivs i inmatningstexten. Vi tar upp problemet med noggrannhet och hastigheten i processen genom att integrera en mapper-nätverk. Slutligen föreslår vi en optimerad mapper som kallas TD-GEM för att uppnå högkvalitativ bildredigering på ett lösgjort sätt. Våra empiriska resultat visar att den föreslagna metoden kan redigera modeobjekt för att ändra färg och ärmens längd.

Artificiell intelligens (AI) tar alltmer plats i människors vardag. Ett område där det nyligen börjat användas i är bildgenerering och konstskapande. Då AI-tekniken inom bildgenerering är ny, har lite forskning gjorts kring hur det kan påverka konstnärer. Tidigare digitala framsteg som lett till verktyg som Photoshop har visats expandera hur konstnärer kan skapa konst och effektiviserat deras kreativa process. Bildgenererande AI, till skillnad från tidigare verktyg som Photoshop, kan generera egna bilder baserat på användarens indata. Detta väcker intresse kring förståelse om hur bildgenererande AI kommer potentiellt kunna påverka konstnärers kreativa process. Studiens mål är att utforska hur bildgenererande AI kan stötta konstnärer i den kreativa processen.  I studien användes en kvalitativ ansats för att fördjupa sig i ämnesområdet och besvara forskningsfrågan. En litteraturstudie som undersökte relevanta ämnen inom ämnesområdet utfördes vilket resulterade i tre aspekter, kontroll, samskapande och idégenerering. Kontroll var viktigt för stöttandet av användares nyttjande av AI. Samskapande och idégenerering var viktiga pelare som stöttar den kreativa processen. Dessa aspekter låg till grund för den empiriska studien. Den empiriska studien bestod av en sju dagars dagboksstudie där konstnärer fick prova tre olika typer av bildgenererande AI. Dagboksstudien kompletterades med intervjuer för att djupare förstå hur bildgenererande AI kunde stötta deras kreativa process. Studiens resultat visar på att bildgenererande AI kan användas för att stötta konstnärers kreativa process då det används som inspiration. Som tillägg identifierades tre förutsättningar som bör bemötas för att konstnärer ska kunna nyttja bildgenererande AI i deras kreativa process. / Artificial intelligence (AI) is increasingly becoming a part of people's daily lives. One area where it has recently been used is in image generation and art creation. As AI technology for image generation is new, little research has been done on how it may affect artists. Previous digital advancements, that led to tools such as Photoshop, have expanded how artists can create art and streamlined their creative process. Image-generating AI, unlike previous tools like Photoshop, can generate its own images based on user input. This raises interest in understanding how image-generating AI may potentially impact artists' creative process. The study aims to explore how image-generating AI can support artists in the creative process. The study used a qualitative approach to delve into the subject area and answer the research question. A literature review investigating relevant topics within the subject area was conducted, resulting in three aspects, control, co-creation, and idea generation. Control was important in supporting users' utilization of AI for their purposes. Co-creation and idea generation were important pillars that support the creative process. These aspects formed the basis for the empirical study. The empirical study consisted of a seven-day diary study where artists were given the opportunity to try three different types of image-generating AI. The diary study was complemented with interviews with the study participants to gain a deeper understanding of how image-generating AI could support their creative process. The study's results show that image-generating AI can be used to support artists' creative process when used as inspiration. In addition, three prerequisites were identified that need to be met for artists to be able to use image-generating AI in their creative process.