・表示された一覧からワークフローを選ぶ ③「image_flux3_klein_t2i: Text to Image」 ④「image_flux3_klein_image_edit: Image Edit」 ⑤「image_flux3_klein_distilled_t2i: Text to Image(蒸留版)」 ⑥「image_flux3_klein_distilled_image_edit: Image Edit(蒸留版)」
・ワークフローでエラーが発生する場合はモデルの配置を確認する
Text to Image 生成画像
Text to Image ワークフロー 動作確認を行ってから保存する
プロンプト
close up profile of a young male athlete with closed eyes pressing his sweaty forehead against a soccer ball, right hand gripping the ball, stark white background, athletic jacket, white ball with jagged red graphic patterns, high contrast studio lighting, highly detailed skin texture, sharp focus Absolutely no text, no typography, no letters, no words, no numbers, no logos, no watermark, no captions, pure imagery only.
Close-up studio photograph against a stark white seamless background, high-contrast directional lighting from the upper left creating hard-edged shadows and bright highlights. A young male athlete in his early twenties with medium brown skin is shown in strict profile facing right, filling nearly the entire frame. His eyes are closed as he presses his sweaty forehead firmly into the center of a soccer ball. Beads of sweat cover his brow, temple, cheekbone, and nose, with several droplets running toward his jaw; pores, fine facial hairs, creases around the eyelids, and damp strands of short black hair remain sharply resolved. He wears a fitted dark navy athletic jacket with a plain raised collar and no markings. On the right, his bent arm wraps around the ball, and his right hand grips its lower side with curled fingers pressing into the textured surface. The white soccer ball has jagged red graphic patterns formed only from angular geometric shapes across its pentagonal panels, without symbols or lettering. Its curved seams, pebbled synthetic texture, scuff marks, and compressed contact point beneath his forehead are crisp. Hard light catches the sweat on his scalp and knuckles while deep shadow defines the underside of his face, neck, hand, and ball. Pure imagery fills the composition, consisting entirely of the athlete and unmarked soccer ball against uninterrupted white.
You are the prompt upsampler of a text-to-image model. Expand the user's short request into ONE detailed, self-contained caption: the exact text the image model receives. Output only the caption, with no greetings, explanations, refusals, questions, Markdown, headings, JSON, coordinates, ids or angle-bracket tokens, and no quotes around it. If the input is not clearly an image request, caption a visualization of its concept. The request may begin with a "TARGET CANVAS: W:H" line: compose for that canvas (wide spreads content sideways, tall stacks it) and never mention the ratio or the canvas.
Fidelity and planning: keep every explicit subject, attribute, count, spatial constraint, style cue and piece of wording; never contradict, substitute, drop or narrow the request, and keep an abstract concept abstract. Decide everything left open as ONE concrete, consistent plan; never offer alternatives or hedge. Never re-express a stated constraint through another mechanism; add camera optics (depth of field, bokeh, blur) only when asked for or implied. Without a stated style, plan an actual photograph and open with the medium convention ("Full-color outdoor photograph, ...", "Full-color indoor photograph, ...", "Studio photograph, ...", "Close-up photograph, ..."); keep "Photorealistic" for renders, and turn "photorealistic" or "realistic" requests for photos into the photograph convention. Give a photograph a few ordinary, non-ideal specifics drawn from the scene's own objects instead of the stock-photo ideal. Do not invent names, brands, logos or celebrities; keep user-named ones. A long request keeps its content but not its wording: drop appraisal and sales vocabulary, turn moods into observable physical facts, and add only new concrete content with positions. Time of day is lighting, not rendered text.
Caption format: one continuous prose block in the generative voice, never "this image shows", "we can see" or "is visible". Lead with medium and style, then scene, lighting and camera, then the subjects with concrete colors, materials and state. Every person in focus gets an observable profile: ethnicity, gender, age range, skin tone ("fair skin", "brown skin"), hair and clothing. Make the layout reconstructable from words: frame-relative positions (frame-left, frame-right, upper, lower, foreground, midground, background), sentence-initial anchors ("On the left, ...", "In the background, ..."), relations (holds, faces, behind) and a consistent order; describe up to about ten instances one by one, beyond that give the exact count and arrangement. Out-of-focus or distant planes are shapes, colors and silhouettes, never identities or readable text, and the background takes about a sixth of the caption. Be definite: no hedging adverbs, no quality or emotion judgments, no closing sentence about mood; state negations as what is present. Rendered text: transcribe every wording verbatim inside double quotes in its original language and script, keep the line breaks of multi-line text, and give its typography, color and placement; author concrete, domain-correct wording when the request needs text it does not supply, and name canonical structures (calendar, keyboard, periodic table) exactly with their full layout. All prose is English; only quoted text keeps its language. Typical length is 100 to 350 words, more for complex scenes.
Text to Image distilled(蒸留版) ワークフロー 動作確認を行ってから保存する
プロンプト
生成画像
A cinematic, Dutch angle night shot of a retro hotel entrance illuminated by neon cyan and warm orange lights. A bellhop in uniform pulls a gold luggage cart with suitcases across a wet sidewalk. Inside the brightly lit, teal-toned glass lobby, two women in vintage uniforms stand near a wooden desk alongside tropical plants and a seated figure. The scene features a moody, stylized teal-and-orange color palette with strong neon reflections. Absolutely no text, no typography, no letters, no words, no numbers, no logos, no watermark, no captions, pure imagery only.
Full-color outdoor photograph at night, shot from a pronounced Dutch angle with the horizon tilted diagonally across the frame. A retro hotel entrance fills the scene, its dark teal facade and broad glass doors illuminated by cyan neon tubes and warm orange light spilling through the lobby windows. In the foreground, rain-darkened pavement slopes upward on account of the tilt, covered in shallow puddles that mirror long streaks of cyan, amber, and gold. Near the center, a Black male bellhop in his forties with brown skin and short black hair wears a burgundy tailcoat with brass buttons, white gloves, a matching peaked cap, striped trousers, and polished black shoes. He leans forward while pulling a curved gold luggage cart toward the entrance, both gloved hands gripping its handle. The cart carries three worn suitcases: a large oxblood suitcase at the bottom, a scuffed tan leather case above it, and a smaller dark green case secured near the top. Water beads cling to the metal rails, which cast broken reflections across the wet sidewalk. Inside the brightly lit teal-toned glass lobby, two women in vintage uniforms stand beside a wooden reception desk. On the left is a white woman in her thirties with fair skin and pinned blonde hair, wearing a fitted cream blouse, teal jacket, and high-collared skirt; beside her stands an East Asian woman in her twenties with fair skin and dark hair arranged in a low bun, wearing a matching teal uniform dress. Both face inward toward the desk without looking at the camera. Behind them sits a seated figure in shadow beneath a shaded lamp, partly hidden by the counter. Tall monstera leaves and palm fronds rise around the desk, their silhouettes edged by turquoise light. Orange lamps glow behind the figures, illuminating wood paneling and patterned curtains made entirely of abstract color and texture. Every surface remains free of typography, symbols, branding, signage, captions, and watermarks.
Replace the earring with a single large openwork metal statement earring, one bold curved pendant, intricate hollow metal cutouts, layered metal wires, polished warm bronze finish, structured artistic shape, keep it attached to the correct ear position, match the character's existing lighting, shadows and skin tone, no pearls, no pearl beads, no scattered small beads.
Close-up portrait of a young japanease woman in her 20s, natural makeup, soft expression. 85mm lens, f/1.4, shallow depth of field, bokeh background. Soft window light from the left, golden hour glow, warm skin tones. Cinematic, realistic, high detail, professional photography. NOT: oversaturated, anime style, low resolution, distorted face.
&ref(): File not found: "8501_2026-10-19_00001_m.jpg" at page "ComfyUI20";
&ref(): File not found: "8501_2026-10-19_00002_m.jpg" at page "ComfyUI20";
&ref(): File not found: "8501_2026-10-19_00003_m.jpg" at page "ComfyUI20";
&ref(): File not found: "8501_2026-10-19_00004_m.jpg" at page "ComfyUI20";
Image Edit ワークフローを整理する
プロンプト
change the dress color to red
ドレスの色を赤に変更する
入力画像
生成画像
FLUX3 Image Edit ワークフロー
&ref(): File not found: "8502_2026-10-19_00001_m.jpg" at page "ComfyUI20";
「FLUX3/」8502_flux3_klein_image_edit.json
Text to Image distilled(蒸留版) ワークフローを整理する
プロンプト
8501 FLUX3 Text to Image distille ワークフロー
Close-up portrait of a young japanease woman in her 20s, natural makeup, soft expression. 85mm lens, f/1.4, shallow depth of field, bokeh background. Soft window light from the left, golden hour glow, warm skin tones. Cinematic, realistic, high detail, professional photography. NOT: oversaturated, anime style, low resolution, distorted face.