Model
Trends
.ai
Model
Trends
.ai
de beste open source AI-modellen
Lokaal uitvoeren
redqw21UNLOCKEDV2TI2I_hyperPONY2024.safetensors
6.46 GB · SafeTensor · fp16 · full
Downloads worden geleverd door Civitai. Sommige makers vragen eerst om in te loggen op Civitai.
AD
<mist-xl>
Over dit model
STABLE DIFFUSION XL 1.0 · Basismodellen
Gemaakt door
AiMetatron
op Civitai
Notities van de maker
REDQW21-UNLOCKED SEP EVENT OVER STAY TUNED 09/30 REDQW21(UNLOCKED) v2 发布 TI2I 多参图生图版本（沿用T2I工作流即可） 天冷了注意保暖！穿衣加强 模型仅用于学习和研究 Built with Qwen The model is FREE. The Key is NOT. CAN YOU FIND IT ? 免費下載 ，自行研究隱藏的採樣方案，成功返圖並分享你的研究即可獲得 888 BUZZ；如果不想自己「解謎」，也可以購買完整 。 を無料でダウンロードし、隠されたサンプリング設定を自分で研究してください。成果画像と研究内容を共有すれば 888 BUZZ を獲得できます。自分で「謎解き」をしたくない場合は、完全な を購入することもできます。 Download the for free, research the hidden sampling setup yourself, and earn 888 BUZZ by sharing your results and research; if you don't want to solve the puzzle yourself, you can also purchase the complete THE ‘SECRET’ KEY Qwen-Image 2.1 · Alignment Challenge · 888/Post 模型非商业用户免费下载。配套的采样设置并不公开 我们发布一个经过特殊训练与推理设计的 Qwen-Image 2.1 Fine-tune，但不会公开完整的「Alignment Key」——包括特殊采样器、采样步数、Sigma 曲线、APG / FreSca 参数、Guidance、权重偏移以及后期处理流程等。 你可以免费下载模型，并使用 ComfyUI、Diffusers 或任何其他推理环境自行研究、实验和尝试复现我们的参考效果。，定价 88800 Buzz，活动开始后会有折扣。它是一套已经调好的 ComfyUI 流程，用来稳定出图。页面上的例图大多是随机种子生成的，几乎没有 Cherry pinking。 工作流里不含 Qwen 模型，也不含这个微调。 This fine-tune is based on Qwen Image 2.1. The training steps, the sampler, and the weight shift at inference were all set separately. The sampling method, step count, curve, and finish are not listed. ComfyUI or any other setup is fine. From testing so far, matching the result takes some trial and error. at 88,800 Buzz, with a discount after the event starts. It is a tuned ComfyUI setup for more stable output. Most of the sample images were generated directly from random seeds. The workflow does not include the Qwen model or this fine-tune. 以上内容只用于学习和研究。工作流的收入是我个人的劳动所得。这个项目没有接受 Qwen Image 开发团队的资金或技术支持，沉默与傲慢是大厂的统一回复。Qwen Image 2.1 目前是研究许可，不能用于商用。 这个微调基于 Qwen Image 2.1。训练步数、采样器，以及推理时的权重偏移，都做过单独处理。采样方式、步数、sigmas曲线和后期没有写出来。用 ComfyUI 或其他环境都可以试。以目前的经验，要把结果对齐，需要自己多试几次。 这是一场关于 Qwen-Image 2.1 推理与采样 的公开挑战 我发布的是一个经过特殊训练、特殊步数、特殊采样器，以及特殊 APG / FreSca 权重偏移处理的 Fine-tune。完整的对齐钥匙不公开。采样方案、采样步数、Sigma 曲线、APG / FreSca 参数、Guidance、权重偏移、后期方案，都在那把钥匙里。缺一环，结果就会偏。 你可以免费下载模型，并使用 ComfyUI、Diffusers 或任何其他推理环境自行研究、实验和尝试复现我们的参考效果。 这并不简单。 但这正是游戏的一部分。 如果你通过自己的研究找到了优秀的参数组合，欢迎把作品和你的实验结果发布到模型页面。我们会通过 Buzz 回馈那些真正投入时间进行研究、实验并取得有价值成果的挑战者。购买商业 Workflow 的用户同样可以参与并获得回馈。（回馈BUZZ以Posts帖子为单位） This project and its challenge are intended solely for learning, experimentation and research purposes. The commercial Workflow is my own work and its BUZZ revenue represents compensation for my independent workflow development and research. I have received no financial or technical support from the Qwen-Image development team for this project. My work on this project has been conducted independently, without official technical assistance, funding, or endorsement from the Qwen-Image team. Qwen-Image and this project are not affiliated with, sponsored by, or endorsed by the Qwen-Image development team unless explicitly stated otherwise. 付费对齐工作流 不想猜的人，走短的那条路，。活动启动后会有促销折扣。 House rules - Download the fine-tune and do the research yourself. - Post the result on this model page and write down what you tried. - A qualifying post pays 888 BUZZ. Workflow buyers included. - Publishing what you found is part of the research. - If you want the stable state without the hunt, . 技术解释 Technical explanation APG / FreSca 这两种做法都不改模型文件，只在采样时处理「引导」这股推力。平时说的 CFG，就是沿着提示词的方向推：推得越紧，画面越贴提示词，也越容易过。 APG 管的是引导的方向。它同样往提示词上推，但会先把这股推力拆开，把容易推过头的部分压下去。说得具体一点，就是在推理时对引导向量做投影，再按情况抑制。 FreSca（Frequency Scaling Guidance）管的是引导信号里的低频和高频。正向条件和负向条件相减，得到引导，再按频率拆开处理，然后加回去。低频大致对应构图、大块色调、明暗和物体的整体形状；高频大致对应纹理、边缘和细小结构。两边可以分开调节。例如构图保持原来的力度，只把细节加强一点；或者少推细节，把构图的引导留下来。 APG / FreSca ,Neither of these changes the model file. Both only adjust the guidance push during sampling. CFG is the usual version of that push: it moves the result toward the prompt. A stronger push follows the prompt more closely, and it also overshoots more easily. APG controls the direction of that guidance. It still pushes toward the prompt, but it splits the push first and holds back the part that tends to go too far. More precisely, it projects the guidance vector during inference and then suppresses it where needed. FreSca (Frequency Scaling Guidance) controls the low and high frequencies inside the guidance signal. It takes the difference between the positive and negative conditions, splits that guidance by frequency, and adds it back afterward. Low frequency mostly corresponds to composition, broad color, light and dark, and the overall shape of objects. High frequency mostly corresponds to texture, edges, and small detail. The two can be adjusted separately. Composition can stay as it is while detail is guided a little harder, or detail can be pushed less while the guidance for composition is kept. 大量例图来自 和 的努力更新和持续开放，也感谢社区里认真做作品的各位。 只用于学习和研究 这场游戏只用于学习和研究。 Fine-tune: Built with Qwen, Applicable to Qwen-Image-2.1 Workflow: Built with ComfyUI Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) 2026 Hangzhou Tongyi Laboratory Technology Co., Ltd. All Rights Reserved. Learning and research only This game is for learning and research. Fine-tune: Built with Qwen, Applicable to Qwen-Image-2.1 Workflow: Built with ComfyUI Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) 2026 Hangzhou Tongyi Laboratory Technology Co., Ltd. All Rights Reserved. REDKREA2-Alternating Evaluation REDGPT2-Turbo-逼真剧创 The Grand Pussy Truth 普世真理 KREA2 GPT2 逼真剧创 Alternating Evaluation | MIST3 9/2/2026 采用 SDA（语义方向对齐）训练——基于教师指导的多样性对齐损失，结合 Forward XM 最佳-5候选者探索方法，在单节点高噪声（σ = 0.9567）上完成训练。本方案已取得 商业使用授权，采用双模型高低区 sigmas（特指降噪参数序列）交叉去噪，4H+6L 交叉。 本模型隶属于 AiMetatron Paid Access 模型服务包，所有购买了 红潮/黑兽 H3 服务的用户可以找我获取授权下载地址。单独在本站购买 REDKREA2 仅获得本页面模型的Access。 免费商业使用的条件 Krea 2 是 公司发布的 AI 图像生成模型，提供两个可下载变体：Krea 2 Raw 和 Krea 2 Turbo。其商业使用受 Krea 2 Community License Agreement（社区许可协议）​ 约束。在社区许可协议下，免费商业使用 的前提是：你（包括所有共同所有或控制的关联实体）的全公司年总收入低于 100 万美元（$1,000,000 USD）​，按过去 12 个月滚动计算。 输出的所有权 - 你拥有你生成的输出（Outputs）​，前提是你遵守本协议。 - Krea 对输出不主张所有权。 - 你需对输出的内容、准确性、合法性以及使用或分发的一切后果承担全部责任。 Trained with SDA (Semantic Directional Alignment) — a teacher-guid
Triggerwoorden
1Girl
Any_girl
Chinese Hanfu
6,534 downloads · 610 likes op Civitai
SHA256
DB0525A2BC636101B8E2B90F6C2772AFDE33FF629B7EE41379CE38A521A810B8
ModelTrends.ai model-ID
#9425
Inhoud melden
Voorbeeldrenders
Prompts en instellingen gedeeld door de mensen die deze renders op Civitai maakten. Kies een render om te zien hoe hij is gemaakt.
Instellingen
Sampler
Euler
Stappen
12
Guidance
1
Seed
305146871341860
Formaat
4800x2688
Gebruikt gewicht
0.2
Prompt
Shot on iPhone 15 Pro Max main camera, 24mm lens equivalent. Computational photography, HDR processing, deep depth of field with everything in focus, sharp lifelike textures, unedited raw everyday smartphone photography, natural ambient lighting. Scene: A surreal painterly scene of a tiny man standing in the middle of an enormous golden wheat field beneath a bright blue afternoon sky, pulling downward on a gigantic invisible zipper running vertically through the heavens. Behind the opening is revealed a completely different world: deep midnight space filled with brilliant stars, violet nebulae and an enormous luminous crescent moon. The edges of the blue daytime sky curl outward like physical fabric around the opening. Golden sunlight illuminates one side of the man while cold blue moonlight illuminates the other. Dramatic symmetry, impossible visual concept, rich complementary colors, sweeping clouds, cinematic scale, playful yet breathtaking surrealism. ,
Negatieve prompt
unknown
Instellingen
Formaat
960x1920
Prompt
"subject": "description": "A charming young East Asian woman in her early 20s with fair porcelain skin, taking a casual intimate selfie indoors.", "mirror_rules": "Selfie-style direct engagement with viewer, natural arm position implied", "age": "early 20s", "expression": "eyes": "look": "wide open, bright and slightly playful", "energy": "gentle, curious, sweet", "direction": "looking straight at the camera" , "mouth": "position": "soft natural smile with upturned corners", "energy": "approachable and lighthearted" , "overall": "sweet, intimate, slightly shy yet engaging expression" , "face": "preserve_original": "soft jawline, full cheeks, natural double eyelids, delicate features", "makeup": "light natural makeup, subtle blush, glossy coral-red lips, dewy skin finish" , "hair": "color": "jet black", "style": "short bob haircut with straight full bangs and soft layers framing the face", "effect": "smooth, shiny, healthy with natural movement" , "body": "frame": "petite and slim", "waist": "slender", "chest": "natural full bust with visible cleavage", "legs": "not visible", "skin": "visible_areas": "face, neck, shoulders, upper chest and collarbone", "tone": "fair porcelain with warm undertones", "texture": "smooth and soft with natural subtle texture and pores", "lighting_effect": "warm golden sunlight creating soft highlights, gentle shadows and radiant dewy glow" , "pose": "position": "upper body slightly angled toward camera in relaxed selfie pose", "base": "seated or standing indoors", "overall": "intimate and natural, one hand gently holding and lifting the bonnet edge" , "clothing": "top": "type": "delicate white camisole with thin spaghetti straps", "color": "off-white / cream", "details": "sheer lace trim along neckline and straps, low neckline, soft lightweight fabric", "effect": "feminine, soft, slightly revealing with natural drape" , "bottom": "type": "light-colored garment", "color": "white or off-white", "details": "partially visible at frame bottom" , "accessories": "headwear": "white sheer lace bonnet with ruffles, frills and delicate details, playfully held and lifted by hand", "jewelry": "small stud earrings", "device": "smartphone (implied for selfie)", "prop": "lace bonnet being adjusted" , "photography": "camera_style": "casual smartphone selfie, realistic documentary style", "angle": "slightly low / eye-level close-up with gentle upward tilt", "shot_type": "medium close-up, chest up, vertical composition", "aspect_ratio": "portrait (approximately 3:4 or 9:16)", "texture": "high detail on skin, hair strands, lace fabric and wood grain", "lighting": "natural warm golden hour side sunlight, soft window light, beautiful highlights and gentle shadows", "depth_of_field": "shallow depth of field, sharp subject, softly blurred background" , "background": "setting": "cozy indoor domestic space, bedroom or dressing area with wooden furniture", "wall_color": "warm natural wood tones", "elements": ["wooden wardrobe/closet", "hanging clothes and garments in upper background", "wooden furniture", "plaid fabric item lower right"], "atmosphere": "warm, intimate, lived-in home feeling", "lighting": "bright natural side lighting, golden tones, soft and flattering" , "the_vibe": "energy": "gentle, cute, playful and intimate", "mood": "sweet, relaxed, charming everyday moment", "aesthetic": "soft feminine / coquette-inspired with natural light and lace, realistic beauty photography", "authenticity": "genuine candid photo feel, natural lighting and subtle imperfections", "intimacy": "high — direct eye contact, close framing, personal gesture of adjusting bonnet", "story": "a young woman enjoying warm sunlight at home, playfully trying on a cute lace accessory and capturing a lighthearted self-portrait", "caption_energy": "light, positive, cute daily-life share (Xiaohongshu style)" , "constraints": "must_keep": [ "short black bob with straight bangs", "white sheer ruffled lace bonnet being held and lifted by hand", "white thin-strap camisole with lace trim and visible natural cleavage", "warm golden side sunlight with soft highlights and shadows", "fair dewy skin with natural glow and texture", "direct wide-eyed gaze and soft smile", "cozy wooden indoor background with soft bokeh", "realistic smartphone selfie photography style" ], "avoid": [ "heavy or dramatic makeup", "studio flash or harsh lighting", "full body or wide shot", "anime, illustration or overly stylized look", "overly perfect/airbrushed skin", "dark or moody atmosphere", "distorted anatomy or unnatural pose" ] , "negative_prompt": [ "blurry", "low quality", "deformed", "bad anatomy", "extra limbs", "mutated hands", "poorly drawn face", "bad proportions", "watermark", "text", "overexposed", "underexposed", "harsh shadows", "plastic skin", "doll-like", "cartoon" ]
Instellingen
Formaat
960x1920
Prompt
"subject": "description": "A charming young East Asian woman in her early 20s with fair porcelain skin, taking a casual intimate selfie indoors.", "mirror_rules": "Selfie-style direct engagement with viewer, natural arm position implied", "age": "early 20s", "expression": "eyes": "look": "wide open, bright and slightly playful", "energy": "gentle, curious, sweet", "direction": "looking straight at the camera" , "mouth": "position": "soft natural smile with upturned corners", "energy": "approachable and lighthearted" , "overall": "sweet, intimate, slightly shy yet engaging expression" , "face": "preserve_original": "soft jawline, full cheeks, natural double eyelids, delicate features", "makeup": "light natural makeup, subtle blush, glossy coral-red lips, dewy skin finish" , "hair": "color": "jet black", "style": "short bob haircut with straight full bangs and soft layers framing the face", "effect": "smooth, shiny, healthy with natural movement" , "body": "frame": "petite and slim", "waist": "slender", "chest": "natural full bust with visible cleavage", "legs": "not visible", "skin": "visible_areas": "face, neck, shoulders, upper chest and collarbone", "tone": "fair porcelain with warm undertones", "texture": "smooth and soft with natural subtle texture and pores", "lighting_effect": "warm golden sunlight creating soft highlights, gentle shadows and radiant dewy glow" , "pose": "position": "upper body slightly angled toward camera in relaxed selfie pose", "base": "seated or standing indoors", "overall": "intimate and natural, one hand gently holding and lifting the bonnet edge" , "clothing": "top": "type": "delicate white camisole with thin spaghetti straps", "color": "off-white / cream", "details": "sheer lace trim along neckline and straps, low neckline, soft lightweight fabric", "effect": "feminine, soft, slightly revealing with natural drape" , "bottom": "type": "light-colored garment", "color": "white or off-white", "details": "partially visible at frame bottom" , "accessories": "headwear": "white sheer lace bonnet with ruffles, frills and delicate details, playfully held and lifted by hand", "jewelry": "small stud earrings", "device": "smartphone (implied for selfie)", "prop": "lace bonnet being adjusted" , "photography": "camera_style": "casual smartphone selfie, realistic documentary style", "angle": "slightly low / eye-level close-up with gentle upward tilt", "shot_type": "medium close-up, chest up, vertical composition", "aspect_ratio": "portrait (approximately 3:4 or 9:16)", "texture": "high detail on skin, hair strands, lace fabric and wood grain", "lighting": "natural warm golden hour side sunlight, soft window light, beautiful highlights and gentle shadows", "depth_of_field": "shallow depth of field, sharp subject, softly blurred background" , "background": "setting": "cozy indoor domestic space, bedroom or dressing area with wooden furniture", "wall_color": "warm natural wood tones", "elements": ["wooden wardrobe/closet", "hanging clothes and garments in upper background", "wooden furniture", "plaid fabric item lower right"], "atmosphere": "warm, intimate, lived-in home feeling", "lighting": "bright natural side lighting, golden tones, soft and flattering" , "the_vibe": "energy": "gentle, cute, playful and intimate", "mood": "sweet, relaxed, charming everyday moment", "aesthetic": "soft feminine / coquette-inspired with natural light and lace, realistic beauty photography", "authenticity": "genuine candid photo feel, natural lighting and subtle imperfections", "intimacy": "high — direct eye contact, close framing, personal gesture of adjusting bonnet", "story": "a young woman enjoying warm sunlight at home, playfully trying on a cute lace accessory and capturing a lighthearted self-portrait", "caption_energy": "light, positive, cute daily-life share (Xiaohongshu style)" , "constraints": "must_keep": [ "short black bob with straight bangs", "white sheer ruffled lace bonnet being held and lifted by hand", "white thin-strap camisole with lace trim and visible natural cleavage", "warm golden side sunlight with soft highlights and shadows", "fair dewy skin with natural glow and texture", "direct wide-eyed gaze and soft smile", "cozy wooden indoor background with soft bokeh", "realistic smartphone selfie photography style" ], "avoid": [ "heavy or dramatic makeup", "studio flash or harsh lighting", "full body or wide shot", "anime, illustration or overly stylized look", "overly perfect/airbrushed skin", "dark or moody atmosphere", "distorted anatomy or unnatural pose" ] , "negative_prompt": [ "blurry", "low quality", "deformed", "bad anatomy", "extra limbs", "mutated hands", "poorly drawn face", "bad proportions", "watermark", "text", "overexposed", "underexposed", "harsh shadows", "plastic skin", "doll-like", "cartoon" ]
Instellingen
Sampler
Euler a
Stappen
10
Guidance
2
Seed
3864876451
Formaat
640x1280
Prompt
Realistic,1 girl, white short hair, eye highlights, dress, short puffy sleeves, frills, outdoors, flower, fluttering petals, upper body, depth of field, (:d:0.8), chromatic aberration abuse,pastel color, Depth of field,garden of the sun,shiny,,volumetric lighting, depth of field, cinematic, vibrant, shadows, detailed ,score_9,source_photo
Negatieve prompt
NSFW
Instellingen
Sampler
Euler a
Stappen
10
Guidance
2
Seed
1851534226
Formaat
640x1280
Prompt
1girl,animal ears,Waist bag,bangs,cat ear headphones,cat ears,cyberpunk,headphones,headset,Combat clothing,Sitting posture,Luminous,Multi light source clothing,indoor,Oblique lateral body,full body,science fiction,Luminous clothing,Future technological background,jacket,lips,long hair,looking at viewer,neon lights,night,shoes,sitting,solo,white footwear,white hair,glowing,
Negatieve prompt
NSFW
AI-modellen voor het genereren van afbeeldingen, video en tekst
mist xl is een basismodel voor de Stable Diffusion XL 1.0-familie, vermeld op ModelTrends.ai, een alleen-lezen catalogus van open source AI-modellen voor afbeeldingen, video en tekst. Vergelijk het met andere Stable Diffusion XL 1.0-modellen, bekijk de populariteitsscore om de trend te zien en open het op PirateDiffusion of BitVector om het te proberen.
Bladeren op modelfamilie
Alle modellen bekijken