1const e={ru:{title:"ÐÑомпÑÑ Ð´Ð»Ñ Higgsfield: ÑÑÑÑкÑÑÑа, оÑибки, пÑимеÑÑ",description:"Ðак пиÑаÑÑ Ð¿ÑомпÑÑ Ð´Ð»Ñ Higgsfield Soul 2.0, Soul Cinema и DoP: кÑеаÑивнÑй бÑиÑ, motion presets, Ñазделение задаÑ, ÑипиÑнÑе оÑибки и пÑимеÑÑ.",h1:"Higgsfield: как пиÑаÑÑ Ð¿ÑомпÑÑ, коÑоÑÑе Ð¼Ð¾Ð´ÐµÐ»Ñ Ð¿Ð¾Ð½Ð¸Ð¼Ð°ÐµÑ",intro:"Higgsfield â плаÑÑоÑма Ñ Ð¿ÑопÑиеÑаÑнÑми моделÑми Soul 2.0 (image, до 4K), Soul Cinema (era-aware image) и DoP (image-to-video, 5 ÑекÑнд, 720â1080p, 100+ motion presets). Soul Ð¿Ð¾Ð½Ð¸Ð¼Ð°ÐµÑ ÑÑбкÑлÑÑÑÑнÑе ÐºÐ¾Ð´Ñ Ð¸ микÑоÑÑÐµÐ½Ð´Ñ Ð½Ð°Ñивно, DoP пÑÐ¸Ð½Ð¸Ð¼Ð°ÐµÑ ÐºÐ¾ÑоÑкие команднÑе пÑомпÑÑ â одно дейÑÑвие плÑÑ Ð¾Ð´Ð½Ð¾ движение камеÑÑ Ð·Ð° Ñаз.",sections:[{heading:"ЧÑо Ð²Ñ Ð¾Ð´Ð¸Ñ Ð² ÑемейÑÑво Higgsfield",body:`Soul 2.0 â image-Ð¼Ð¾Ð´ÐµÐ»Ñ Ñ ÑазÑеÑением до 4K, Ñежимами T2I и I2I, 20+ ÑÑилевÑми пÑеÑеÑами и ÑиÑÑемой Soul ID Ð´Ð»Ñ ÐºÐ¾Ð½ÑиÑÑенÑноÑÑи пеÑÑонажей. ÐÐ¾Ð½Ð¸Ð¼Ð°ÐµÑ ÑÑÑн-ÑеÑминологиÑ, ÑÑбкÑлÑÑÑÑнÑй ÑзÑк, микÑоÑÑÐµÐ½Ð´Ñ («phone flash», «disposable camera», «Y2K street»). 2 3Soul Cinema â оÑделÑÐ½Ð°Ñ image-Ð¼Ð¾Ð´ÐµÐ»Ñ Ñ ÑокÑÑом на кинемаÑогÑаÑиÑеÑÐºÐ¸Ñ ÐºÐ»ÑÑевÑÑ ÐºÐ°Ð´ÑÐ°Ñ . ÐлÑбокие ÑекÑÑÑÑÑ, плÑноÑное зеÑно, ÑÑилизаÑÐ¸Ñ Ð¿Ð¾Ð´ ÑÐ¿Ð¾Ñ Ð¸ (70s, 90s). ÐÐ¾Ð´Ñ Ð¾Ð´Ð¸Ñ Ð´Ð»Ñ ÑаÑкадÑовок и конÑепÑ-аÑÑа. 4 5DoP â image-to-video моделÑ: 5 ÑекÑнд, 720â1080p, 100+ motion presets (360 Orbit, Dolly In/Out, Whip Pan, FPV Drone, Bullet Time). ТиÑÑ ÑкоÑоÑÑи: Lite (бÑÑÑÑÑй пÑевÑÑ), Turbo (1.5â2à бÑÑÑÑее Standard), Standard (макÑ. каÑеÑÑво).`,bullets:["Soul 2.0: T2I + I2I, до 4K, 20+ ÑÑилевÑÑ Ð¿ÑеÑеÑов","Soul Cinema: era-aware image (70s, 90s), плÑноÑÐ½Ð°Ñ ÑÑилизаÑиÑ","DoP: I2V, 5 ÑекÑнд, 720pâ1080p, 100+ motion presets","Soul ID â конÑиÑÑенÑноÑÑÑ Ð¿ÐµÑÑонажей ÑеÑез неÑколÑко генеÑаÑий","Face/Character Swap â визÑалÑнÑе инÑÑÑÑменÑÑ, без ÑекÑÑовÑÑ Ð¿ÑомпÑов"]},{heading:"СÑÑÑкÑÑÑа пÑомпÑа Ð´Ð»Ñ Soul",body:`ÐÑÐ¾Ð¼Ð¿Ñ Ð´Ð»Ñ Soul 2.0 / Soul Cinema â ÑÑо кÑеаÑивнÑй бÑиÑ, а не ÑпиÑок Ñегов. ФоÑмÑла: [Mood/Aesthetic] + [Subject with visual cues] + [References/Style] + [Technical hints]. 6 7Soul наÑивно Ð¿Ð¾Ð½Ð¸Ð¼Ð°ÐµÑ ÑÑбкÑлÑÑÑÑнÑй и ÑÑÑеÑиÑеÑкий ÑзÑк: «phone flash editorial», «disposable camera Y2K street», «90s film grain», «editorial fashion forward». Ðе нÑжно пеÑеобÑÑÑнÑÑÑ ÑÑи ÑеÑÐ¼Ð¸Ð½Ñ â Ð¼Ð¾Ð´ÐµÐ»Ñ ÑаÑпознаÑÑ ÐºÐ¾Ð´Ñ. 8 9Ðлина: коÑоÑкие-ÑÑедние пÑомпÑÑ. ÐÑÐ±Ð¾Ñ ÑÑилевого пÑеÑеÑа ÑÐ½Ð¸Ð¶Ð°ÐµÑ Ð½ÑÐ¶Ð´Ñ Ð² Ñложном пÑомпÑе. ÐÐ»Ñ I2I (Soul Reference) иÑполÑзÑй ÑеÑеÑенÑное изобÑажение как ÑÑилевой ÑкоÑÑ â пÑÐ¾Ð¼Ð¿Ñ Ð¾Ð¿Ð¸ÑÑÐ²Ð°ÐµÑ Ð½Ð°Ð¿Ñавление, не визÑал.`},{heading:"СÑÑÑкÑÑÑа пÑомпÑа Ð´Ð»Ñ DoP (видео)",body:`DoP пÑÐ¸Ð½Ð¸Ð¼Ð°ÐµÑ ÐºÐ¾ÑоÑкие и пÑÑмÑе пÑомпÑÑ. ФоÑмÑла: [Active verb action] + [Camera direction]. Ðдно дейÑÑвие плÑÑ Ð¾Ð´Ð½Ð¾ движение камеÑÑ Ð·Ð° Ñаз. 10 11ÐÑполÑзÑй акÑивнÑе глаголÑ: «darts through», «leaps across», «crashes into», «glides», «spins». УдалÑй «fillers» â команднÑй ÑÑÐ¸Ð»Ñ ÑабоÑÐ°ÐµÑ Ð»ÑÑÑе опиÑаÑелÑного. 12 13KлÑÑевое пÑавило: Ñазделение задаÑ. ÐÑвеÑение и кадÑиÑование â в пÑомпÑе изобÑÐ°Ð¶ÐµÐ½Ð¸Ñ (Soul). Ðвижение â в видео-пÑомпÑе (DoP). ÐÑвеÑение в видео-пÑомпÑе вÑзÑÐ²Ð°ÐµÑ Ð¼ÐµÑÑание. Motion preset вÑбиÑаеÑÑÑ ÐТÐÐÐЬÐÐ Ð¾Ñ ÑекÑÑового пÑомпÑа â ÑÑо паÑамеÑÑ, не ÑаÑÑÑ Ð¿ÑомпÑа. 14 15«Shot on full-frame cinema camera» в видео-пÑомпÑе повÑÑÐ°ÐµÑ Ñеализм.`},{heading:"Soul ID, HEX, Reference",body:`Soul ID â конÑиÑÑенÑноÑÑÑ Ð¿ÐµÑÑонажей ÑеÑез неÑколÑко генеÑаÑий. ÐÑполÑзоваÑÑ Ñвежие, одноÑипнÑе ÑеÑеÑенÑнÑе ÑоÑо. ÐлавнÑй анÑипаÑÑеÑн â ÑмеÑивание ÑÑаÑÑÑ Ð¸ новÑÑ ÑеÑеÑенÑов: ÑÑо вÑзÑÐ²Ð°ÐµÑ drift иденÑиÑноÑÑи. 16 17Soul HEX â авÑомаÑиÑеÑкое извлеÑение и пÑименение ÑвеÑовÑÑ Ð¿Ð°Ð»Ð¸ÑÑ Ð¸Ð· ÑеÑеÑенÑнÑÑ Ð¸Ð·Ð¾Ð±Ñажений. Ðолезно Ð´Ð»Ñ Ð±ÑендовÑÑ ÑеÑий и моодбоÑдов Ñ ÑикÑиÑованной ÑвеÑовой ÑÑ ÐµÐ¼Ð¾Ð¹. 18 19Soul Reference â I2I Ñ Ð²Ð¸Ð·ÑалÑнÑм ÑкоÑением: загÑÑжаеÑÑ ÑеÑеÑенÑ, пÑÐ¾Ð¼Ð¿Ñ Ð¾Ð¿Ð¸ÑÑÐ²Ð°ÐµÑ ÑÑо измениÑÑ Ð¸Ð»Ð¸ как ÑÑилизоваÑÑ. ЧиÑÑÑй белÑй Ñон на Ð²Ñ Ð¾Ð´Ð½Ð¾Ð¼ изобÑажении â анÑипаÑÑеÑн, не Ñ Ð²Ð°ÑÐ°ÐµÑ Ð³Ð»ÑÐ±Ð¸Ð½Ñ Ð´Ð»Ñ Soul.`},{heading:"Face Swap, Character Swap и ÑиÑÑ DoP",body:`Face Swap и Character Swap â визÑалÑнÑе инÑÑÑÑменÑÑ, ÐРиÑполÑзÑÑÑ ÑекÑÑовÑе пÑомпÑÑ. Face Swap â замена лиÑа в изобÑажении/видео на оÑнове визÑалÑного ввода. Character Swap (Recast) â пеÑÐµÐ½Ð¾Ñ Ð¿Ð¾Ð»Ð½Ð¾Ð³Ð¾ обÑаза: Ñело, мимика, Ñон кожи, движение. 30+ пÑеÑеÑов пеÑÑонажей. ÐÑенка пÑомпÑа Ð´Ð»Ñ ÑÑÐ¸Ñ Ñежимов невозможна â они ÑабоÑаÑÑ Ð±ÐµÐ· ÑекÑÑа. 20 21ТиÑÑ DoP â ÑкоÑоÑÑÑ Ð³ÐµÐ½ÐµÑаÑии, не ÑазнÑе модели: 22 23DoP Lite (2 кÑедиÑа) â ÑамÑй бÑÑÑÑÑй, Ð´Ð»Ñ Ð¿ÑевÑÑ ÐºÐ¾Ð½ÑепÑов. DoP Turbo (6.5 кÑедиÑов) â 1.5â2à бÑÑÑÑее Standard, Ð±Ð°Ð»Ð°Ð½Ñ ÑкоÑоÑÑÑ/каÑеÑÑво. DoP Standard (9 кÑедиÑов) â ÑÑандаÑÑ, макÑималÑное каÑеÑÑво и ÑлÑÑÑеннÑй Ñеализм оÑвеÑениÑ.`}],examples:[{before:"кÑаÑÐ¸Ð²Ð°Ñ Ð´ÐµÐ²ÑÑка в ÑÑиле 90-Ñ ",after:"Phone flash editorial portrait of a young woman with bleached blonde hair and pink eyeshadow, oversized denim jacket, holding a disposable camera, Y2K street aesthetic, slight motion blur, harsh frontal flash, low fashion editorial mood.",note:"Soul 2.0 наÑивно Ð¿Ð¾Ð½Ð¸Ð¼Ð°ÐµÑ Â«phone flash», «disposable camera», «Y2K» â не нÑжно пеÑеобÑÑÑнÑÑÑ. ÐонкÑеÑнÑе ÑÑÑеÑиÑеÑкие ÐºÐ¾Ð´Ñ + ÑÑбÑÐµÐºÑ Ñ Ð²Ð¸Ð·ÑалÑнÑми деÑалÑми + ÑÐµÑ Ð½Ð¸ÐºÐ° ÑÑÑмки."},{before:"the woman walks through the city looking sad and then turns around to look at the camera with cinematic lighting and atmospheric mood",after:"Walks briskly through neon-lit alley, Whip Pan toward camera.",note:"DoP пÑÐ¾Ð¼Ð¿Ñ Ð´Ð¾Ð»Ð¶ÐµÐ½ бÑÑÑ ÐÐÐ ÐТÐÐÐ. Ðдно дейÑÑвие плÑÑ Ð¾Ð´Ð½Ð¾ движение камеÑÑ. ÐÑвеÑение и кадÑиÑование â в Soul-пÑомпÑе, Ð
23½Ðµ в DoP. Motion preset (Whip Pan) â ÑÑо паÑамеÑÑ, вÑбиÑаеÑÑÑ Ð¾ÑделÑно."},{before:"white background portrait, simple, clean",after:"Editorial portrait of a young woman with long dark hair, wearing a cream cashmere sweater, against a soft warm grey studio backdrop, natural window light from the left, fashion-forward mood, shallow depth of field.",note:"ЧиÑÑÑй белÑй Ñон на вÑ
одном изобÑажении â анÑипаÑÑеÑн Ð´Ð»Ñ Soul, не Ñ
ваÑÐ°ÐµÑ Ð³Ð»ÑбинÑ. ÐпиÑание конкÑеÑного Ñона (warm grey backdrop) и оÑвеÑÐµÐ½Ð¸Ñ Ð´Ð°ÑÑ Ð¼Ð¾Ð´ÐµÐ»Ð¸ опоÑÑ Ð´Ð»Ñ ÑендеÑинга."}],mistakes:[{title:"ÐлиннÑе ÑложнÑе пÑомпÑÑ Ð´Ð»Ñ DoP",explain:"DoP â image-to-video Ñ ÑокÑÑом на движении. ÐлиннÑе опиÑаÑелÑнÑе пÑомпÑÑ Ñ Ð¸ÑÑоÑией и ÑмоÑиÑми ÑабоÑаÑÑ Ð¿Ð»Ð¾Ñ
о. ÐоÑоÑкие команднÑе конÑÑÑÑкÑии «Active verb + Camera direction» â ноÑма. ÐÑли Ñ
оÑеÑÑÑ ÑложноÑÑи, пеÑеноÑи ÐµÑ Ð² image-пÑÐ¾Ð¼Ð¿Ñ (Soul), а не в DoP."},{title:"ÐÑвеÑение и обÑекÑив в видео-пÑомпÑе",explain:"ÐÑвеÑение и кадÑиÑование в DoP-пÑомпÑе вÑзÑваÑÑ Ð¼ÐµÑÑание (flicker). ÐÑи паÑамеÑÑÑ Ð´Ð¾Ð»Ð¶Ð½Ñ Ð±ÑÑÑ Ð·Ð°ÑикÑиÑÐ¾Ð²Ð°Ð½Ñ Ð½Ð° ÑÑапе изобÑÐ°Ð¶ÐµÐ½Ð¸Ñ (Soul). Ðидео-пÑÐ¾Ð¼Ð¿Ñ Ð¾Ð¿Ð¸ÑÑÐ²Ð°ÐµÑ ÑолÑко движение и дейÑÑвие. ÐÑо базовое пÑавило ÑÐ°Ð·Ð´ÐµÐ»ÐµÐ½Ð¸Ñ Ð·Ð°Ð´Ð°Ñ Ð¼ÐµÐ¶Ð´Ñ Soul и DoP."},{title:"СмеÑивание ÑÑаÑÑÑ
и новÑÑ
ÑеÑеÑенÑов Ð´Ð»Ñ Soul ID",explain:"Soul ID обеÑпеÑÐ¸Ð²Ð°ÐµÑ ÐºÐ¾Ð½ÑиÑÑенÑноÑÑÑ Ð¿ÐµÑÑонажа ÑеÑез неÑколÑко генеÑаÑий пÑи ÑвежиÑ
, одноÑипнÑÑ
ÑеÑеÑенÑнÑÑ
ÑоÑо. СмеÑивание ÑÑаÑÑÑ
Ñнимков (дÑÑÐ³Ð°Ñ ÑÑÑижка, оÑвеÑение, возÑаÑÑ) и новÑÑ
вÑзÑÐ²Ð°ÐµÑ drift иденÑиÑноÑÑи â Ð¼Ð¾Ð´ÐµÐ»Ñ ÑÑÑеднÑÐµÑ Ð»Ð¸Ñо. ÐÑполÑзÑй 3â5 ÑвежиÑ
ÑоÑо в едином ÑÑиле."},{title:"ЧиÑÑÑй белÑй Ñон на вÑ
одном изобÑажении",explain:"Soul (как T2I, Ñак и I2I) Ñ
Ñже ÑабоÑÐ°ÐµÑ Ñ ÑиÑÑÑм белÑм Ñоном на вÑ
оде â не Ñ
ваÑÐ°ÐµÑ Ð³Ð»ÑÐ±Ð¸Ð½Ñ Ð¸ конÑекÑÑа Ð´Ð»Ñ Ð³ÐµÐ½ÐµÑаÑии. ÐÑполÑзÑй cluttered scene, studio backdrop Ñ Ñоном, или environmental background. ÐÑли Ñон должен бÑÑÑ Ð½ÐµÐ¹ÑÑалÑнÑм, опиÑÑвай его как «soft warm grey backdrop», не «pure white»."},{title:"ÐÑÐ¾Ð¼Ð¿Ñ Ð´Ð»Ñ Face Swap / Character Swap",explain:"Face Swap и Character Swap (Recast) â визÑалÑнÑе инÑÑÑÑменÑÑ, без ÑекÑÑовÑÑ
пÑомпÑов. РабоÑаÑÑ Ð½Ð° оÑнове вÑ
однÑÑ
изобÑажений и пÑеÑеÑов. ÐÑли ÑÑ Ð¿ÑÑаеÑÑÑÑ ÑедакÑиÑоваÑÑ Ð»Ð¸Ñо или обÑаз ÑеÑез ÑекÑÑ Ð² ÑÑиÑ
ÑежимаÑ
â ниÑего не ÑÑабоÑаеÑ. ÐÑполÑзÑй Soul Reference (I2I) Ð´Ð»Ñ ÑекÑÑового ÑедакÑиÑÐ¾Ð²Ð°Ð½Ð¸Ñ Ð¸Ð»Ð¸ Face Swap Ð´Ð»Ñ Ð²Ð¸Ð·ÑалÑного пеÑеноÑа."}],faq:[{q:"Чем оÑлиÑаÑÑÑÑ Soul 2.0, Soul Cinema и DoP?",a:"Soul 2.0 â image-Ð¼Ð¾Ð´ÐµÐ»Ñ Ð´Ð¾ 4K Ñ ÑÑÑн-ÑокÑÑом, Ð¿Ð¾Ð½Ð¸Ð¼Ð°ÐµÑ ÑÑбкÑлÑÑÑÑнÑе ÐºÐ¾Ð´Ñ Ð¸ микÑоÑÑендÑ. Soul Cinema â image-Ð¼Ð¾Ð´ÐµÐ»Ñ Ñ era-aware ÑÑилизаÑией (70s, 90s), плÑноÑное зеÑно, кинемаÑогÑаÑиÑеÑкие клÑÑевÑе кадÑÑ. DoP â image-to-video, 5 ÑекÑнд, 100+ motion presets, пÑÐ¸Ð½Ð¸Ð¼Ð°ÐµÑ ÐºÐ¾ÑоÑкие команднÑе пÑомпÑÑ. ÐÑи модели ÑаÑÑо иÑполÑзÑÑÑÑÑ Ð² ÑвÑзке: Soul/Cinema â клÑÑевой ÐºÐ°Ð´Ñ â DoP анимиÑÑÐµÑ ÐµÐ³Ð¾."},{q:"Ð ÑÑм ÑазниÑа Ð¼ÐµÐ¶Ð´Ñ DoP Lite, Turbo и Standard?",a:"ÐÑо ÑиÑÑ ÑкоÑоÑÑи, не ÑазнÑе модели. DoP Lite (2 кÑедиÑа) â ÑамÑй бÑÑÑÑÑй, Ð´Ð»Ñ Ð¿ÑевÑÑ ÐºÐ¾Ð½ÑепÑов. DoP Turbo (6.5 кÑедиÑов) â 1.5â2à бÑÑÑÑее Standard, баланÑ. DoP Standard (9 кÑедиÑов) â макÑималÑное каÑеÑÑво, ÑлÑÑÑеннÑй Ñеализм оÑвеÑениÑ. ÐÐ»Ñ ÑиÐ
23½Ð°Ð»Ñной пÑодÑкÑии â Standard, Ð´Ð»Ñ Ð¸ÑеÑаÑий â Turbo, Ð´Ð»Ñ Ð±ÑÑÑÑÑÑ ÑеÑÑов â Lite."},{q:"Ðак ÑабоÑÐ°ÐµÑ Soul ID Ð´Ð»Ñ ÐºÐ¾Ð½ÑиÑÑенÑноÑÑи пеÑÑонажа?",a:"ÐагÑÑжаеÑÑ 3â5 ÑÐ²ÐµÐ¶Ð¸Ñ , одноÑипнÑÑ ÑеÑеÑенÑнÑÑ ÑоÑо пеÑÑонажа. Soul ID Ð¸Ð·Ð²Ð»ÐµÐºÐ°ÐµÑ Ð¸Ð´ÐµÐ½ÑиÑноÑÑÑ Ð¸ ÑÐ¾Ñ ÑанÑÐµÑ ÐµÑ ÑеÑез неÑколÑко генеÑаÑий. Ðлавное пÑавило â не ÑмеÑиваÑÑ ÑÑаÑÑе и новÑе ÑоÑо: ÑÐ°Ð·Ð½Ð°Ñ ÑÑÑижка, оÑвеÑение, возÑаÑÑ Ð²ÑзÑваÑÑ drift. ÐдеалÑно â одна ÑеÑÑÐ¸Ñ ÑÑÑмки Ñ ÑазнÑÑ ÑакÑÑÑов в одинаковом ÑÑиле."},{q:"ÐоÑÐµÐ¼Ñ Ð½ÐµÐ»ÑÐ·Ñ ÑедакÑиÑоваÑÑ Ð¾ÑвеÑение в DoP-пÑомпÑе?",a:"ÐÑвеÑение и кадÑиÑование в видео-пÑомпÑе вÑзÑваÑÑ Ð¼ÐµÑÑание (flicker) Ð¼ÐµÐ¶Ð´Ñ ÐºÐ°Ð´Ñами. DoP â image-to-video, и оÑвеÑение должно бÑÑÑ Ð·Ð°ÑикÑиÑовано на ÑÑапе изобÑажениÑ. ÐÑли нÑжно измениÑÑ ÑÐ²ÐµÑ â генеÑиÑÑй новое изобÑажение ÑеÑез Soul Ñ Ð½ÑжнÑм оÑвеÑением, поÑом анимиÑÑй ÑеÑез DoP. ÐÑо базовое пÑавило ÑÐ°Ð·Ð´ÐµÐ»ÐµÐ½Ð¸Ñ Ð·Ð°Ð´Ð°Ñ."},{q:"Ðожно ли иÑполÑзоваÑÑ Face Swap ÑеÑез ÑекÑÑовÑй пÑомпÑ?",a:"ÐеÑ. Face Swap и Character Swap (Recast) â визÑалÑнÑе инÑÑÑÑменÑÑ, ÑабоÑаÑÑ Ð½Ð° оÑнове Ð²Ñ Ð¾Ð´Ð½ÑÑ Ð¸Ð·Ð¾Ð±Ñажений и пÑеÑеÑов, без ÑекÑÑа. ÐÐ»Ñ ÑекÑÑового ÑедакÑиÑÐ¾Ð²Ð°Ð½Ð¸Ñ Ð»Ð¸Ñа или обÑаза иÑполÑзÑй Soul Reference (I2I): загÑÑжаеÑÑ ÑеÑеÑенÑ, пÑÐ¾Ð¼Ð¿Ñ Ð¾Ð¿Ð¸ÑÑÐ²Ð°ÐµÑ Ð¸Ð·Ð¼ÐµÐ½ÐµÐ½Ð¸Ðµ. ÐÑо ÑазнÑе пайплайнÑ."},{q:"Ðакие motion presets поддеÑÐ¶Ð¸Ð²Ð°ÐµÑ DoP?",a:"100+ пÑеÑеÑов, вклÑÑÐ°Ñ 360 Orbit, Dolly In/Out, Whip Pan, FPV Drone, Bullet Time, Tracking. ÐÑбиÑаÑÑÑÑ Ð¾ÑделÑно Ð¾Ñ ÑекÑÑового пÑомпÑа â ÑÑо паÑамеÑÑ, не ÑаÑÑÑ Ð¿ÑомпÑа. Ð DoP-пÑомпÑе опиÑÑвай дейÑÑвие («darts through», «leaps»), а motion preset â ÑеÑез UI или API-паÑамеÑÑ. ÐÑо Ñазделение Ð´ÐµÐ»Ð°ÐµÑ ÑезÑлÑÑÐ°Ñ Ð¿ÑедÑказÑемее."},{q:"ÐоддеÑживаеÑÑÑ Ð»Ð¸ Opten Ð´Ð»Ñ Higgsfield?",a:"Ðа, ÑаÑÑиÑение Opten авÑомаÑиÑеÑки ÑаÑпознаÑÑ Higgsfield Soul 2.0, Soul Cinema и DoP. ÐÑÐµÐ½Ð¸Ð²Ð°ÐµÑ Ð¿ÑомпÑÑ Ð¿Ð¾ ÑÑÑÑкÑÑÑе, опиÑанной вÑÑе: пÑовеÑÑÐµÑ ÐºÑеаÑивнÑй бÑÐ¸Ñ Ð´Ð»Ñ Soul, коÑоÑкий команднÑй пÑÐ¾Ð¼Ð¿Ñ Ð´Ð»Ñ DoP, Ñазделение Ð·Ð°Ð´Ð°Ñ (оÑвеÑение в Soul, движение в DoP), оÑÑÑÑÑÑвие ÑекÑÑовÑÑ Ð¿ÑомпÑов Ð´Ð»Ñ Face/Character Swap. Ðдним кликом можно полÑÑиÑÑ rewrite в пÑавилÑной ÑÑÑÑкÑÑÑе."}]},en:{title:"Higgsfield Prompts: Structure, Mistakes, Examples",description:"How to write prompts for Higgsfield Soul 2.0, Soul Cinema, and DoP: creative brief, motion presets, task separation, common mistakes, and examples.",h1:"Higgsfield: how to write prompts the model actually understands",intro:"Higgsfield is a platform with proprietary models â Soul 2.0 (image, up to 4K), Soul Cinema (era-aware image), and DoP (image-to-video, 5 seconds, 720â1080p, 100+ motion presets). Soul understands subcultural codes and micro-trends natively; DoP accepts short command-style prompts â one action plus one camera move at a time.",sections:[{heading:"What's in the Higgsfield family",body:`Soul 2.0 â image model up to 4K with T2I and I2I modes, 20+ style presets, and a Soul ID system for character consistency. Understands fashion terminology, subcultural language, micro-trends («phone flash», «disposable camera», «Y2K street»). 24 25Soul Cinema â a separate image model focused on cinematic keyframes. Deep textures, film grain, era styling (70s, 90s). Suited for storyboards and concept art. 26
27DoP â image-to-video model: 5 seconds, 720â1080p, 100+ motion presets (360 Orbit, Dolly In/Out, Whip Pan, FPV Drone, Bullet Time). Speed tiers: Lite (fast preview), Turbo (1.5â2à faster than Standard), Standard (max quality).`,bullets:["Soul 2.0: T2I + I2I, up to 4K, 20+ style presets","Soul Cinema: era-aware image (70s, 90s), film-grain styling","DoP: I2V, 5 seconds, 720pâ1080p, 100+ motion presets","Soul ID â character consistency across multiple generations","Face/Character Swap â visual tools, no text prompts"]},{heading:"Soul prompt structure",body:`A Soul 2.0 / Soul Cinema prompt is a creative brief, not a tag list. Formula: [Mood/Aesthetic] + [Subject with visual cues] + [References/Style] + [Technical hints]. 28 29Soul natively understands subcultural and aesthetic language: «phone flash editorial», «disposable camera Y2K street», «90s film grain», «editorial fashion forward». No need to over-explain these terms â the model recognizes the codes. 30 31Length: short-to-medium prompts. Picking a style preset lowers the need for a complex prompt. For I2I (Soul Reference) use the reference image as a stylistic anchor â the prompt describes direction, not the visual.`},{heading:"DoP prompt structure (video)",body:`DoP accepts short, direct prompts. Formula: [Active verb action] + [Camera direction]. One action plus one camera move at a time. 32 33Use active verbs: «darts through», «leaps across», «crashes into», «glides», «spins». Drop fillers â command style beats descriptive style here. 34 35Key rule: task separation. Lighting and framing go in the image prompt (Soul). Motion goes in the video prompt (DoP). Lighting in the video prompt causes flicker. Motion preset is selected SEPARATELY from the text prompt â it's a parameter, not part of the prompt. 36 37«Shot on full-frame cinema camera» in the video prompt boosts realism.`},{heading:"Soul ID, HEX, Reference",body:`Soul ID â character consistency across multiple generations. Use fresh, uniform reference photos. The main antipattern is mixing old and new references â this causes identity drift. 38 39Soul HEX â automatic extraction and application of color palettes from reference images. Useful for brand series and moodboards with a fixed color scheme. 40 41Soul Reference â I2I with visual anchoring: upload a reference, the prompt describes what to change or how to stylize. A pure white background on the input image is an antipattern â there's not enough depth for Soul.`},{heading:"Face Swap, Character Swap, and DoP tiers",body:`Face Swap and Character Swap are visual tools â they do NOT use text prompts. Face Swap â face replacement in an image/video based on visual input. Character Swap (Recast) â full appearance transfer: body, mimic, skin tone, movement. 30+ character presets. Prompt scoring for these modes is impossible â they run without text. 42 43DoP tiers are generation speeds, not different models: 44 45DoP Lite (2 credits) â fastest, for concept previews. DoP Turbo (6.5 credits) â 1.5â2à faster than Standard, balanced. DoP Standard (9 credits) â standard, max quality and improved lighting realism.`}],examples:[{before:"beautiful girl in 90s style",after:"Phone flash editorial portrait of a young woman with bleached blonde hair and pink eyeshadow, oversized denim jacket, holding a disposable camera, Y2K street aesthetic, slight motion blur, harsh frontal flash, low fashion editorial mood.",note:"Soul 2.0 natively understands «phone flash», «disposable camera», «Y2K» â no need to over-explain. Concrete aesthetic codes + subject with visual cues + technique."},{before:"the woman walks through the city looking sad and then turns around to look at the camera with cinematic lighting and atmospheric mood",after:"Walks briskly through neon-lit alley, Whip Pan toward camera.",note:"A DoP prompt should be SHORT. One action plus one camera move. Lighting and framing belong in the Soul prompt, not in DoP. Motion preset (Whip Pan) is a parameter, selected separately."},{before:"white background portrait, simple, clean",after:"Editorial portrait of a young woman with long dark hair, wearing a cream cashmere sweater, against a soft warm grey studio backdrop, natural window light from the left, fashion-forward mood, shallow depth of field.",n
45ote:"A pure white background on the input image is a Soul antipattern â not enough depth. A concrete background (warm grey backdrop) and lighting give the model something to anchor on."}],mistakes:[{title:"Long complex prompts for DoP",explain:"DoP is image-to-video with a focus on motion. Long descriptive prompts with story and emotion work poorly. Short command-style «Active verb + Camera direction» is the norm. If complexity is needed, push it into the image prompt (Soul), not into DoP."},{title:"Lighting and lens in the video prompt",explain:"Lighting and framing in a DoP prompt cause flicker. These parameters should be fixed at the image stage (Soul). The video prompt describes only motion and action. This is the basic task-separation rule between Soul and DoP."},{title:"Mixing old and new references for Soul ID",explain:"Soul ID delivers character consistency across multiple generations with fresh, uniform reference photos. Mixing old shots (different haircut, lighting, age) with new ones causes identity drift â the model averages the face. Use 3â5 fresh photos in one consistent style."},{title:"Pure white background on the input image",explain:"Soul (both T2I and I2I) works worse with a pure white input background â not enough depth or context for generation. Use a cluttered scene, a toned studio backdrop, or an environmental background. If the background must be neutral, describe it as «soft warm grey backdrop», not «pure white»."},{title:"Prompting Face Swap / Character Swap",explain:"Face Swap and Character Swap (Recast) are visual tools, no text prompts. They run on input images and presets. Trying to edit a face or look via text in these modes won't work. Use Soul Reference (I2I) for text-driven editing or Face Swap for visual transfer."}],faq:[{q:"How are Soul 2.0, Soul Cinema, and DoP different?",a:"Soul 2.0 â image model up to 4K with a fashion focus, understands subcultural codes and micro-trends. Soul Cinema â image model with era-aware styling (70s, 90s), film grain, cinematic keyframes. DoP â image-to-video, 5 seconds, 100+ motion presets, accepts short command-style prompts. These models are often chained: Soul/Cinema â keyframe â DoP animates it."},{q:"What's the difference between DoP Lite, Turbo, and Standard?",a:"These are speed tiers, not separate models. DoP Lite (2 credits) â fastest, for concept previews. DoP Turbo (6.5 credits) â 1.5â2à faster than Standard, balanced. DoP Standard (9 credits) â max quality, improved lighting realism. For final production â Standard, for iterations â Turbo, for quick tests â Lite."},{q:"How does Soul ID deliver character consistency?",a:"Upload 3â5 fresh, uniform reference photos of the character. Soul ID extracts identity and preserves it across multiple generations. The key rule â don't mix old and new photos: different haircut, lighting, or age cause drift. Ideal â one photo session from different angles in the same style."},{q:"Why can't lighting be edited in the DoP prompt?",a:"Lighting and framing in the video prompt cause flicker between frames. DoP is image-to-video, and lighting must be locked at the image stage. To change the light â generate a new image via Soul with the desired lighting, then animate via DoP. This is the basic task-separation rule."},{q:"Can Face Swap be used through a text prompt?",a:"No. Face Swap and Character Swap (Recast) are visual tools â they run on input images and presets, without text. For text-driven editing of a face or look, use Soul Reference (I2I): upload a reference, prompt describes the change. These are different pipelines."},{q:"What motion presets does DoP support?",a:"100+ presets including 360 Orbit, Dolly In/Out, Whip Pan, FPV Drone, Bullet Time, Tracking. They're chosen separately from the text prompt â it's a parameter, not part of the prompt. In the DoP prompt, describe the action («darts through», «leaps»); the motion preset goes through the UI or API parameter. This separation keeps results predictable."},{q:"Does Opten support Higgsfield?",a:"Yes, the Opten extension auto-detects Higgsfield Soul 2.0, Soul Cinema, and DoP. It scores prompts against the structure outlined above: creative brief for Soul, short command prompt for DoP, task separation (lighting in Soul, motion in DoP), and absence of text prompts for Face/Character Swap. One
45click delivers a rewrite in the correct structure."}]}};export{e as content};
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.