Model
Trends
.ai
Model
Trends
.ai
ang pinakamahuhusay na open source AI model
Patakbuhin nang lokal
redcraftHybridH3Krea2dual_revealULTRAV35_1145704.safetensors
11.08 GB · SafeTensor · fp8 · pruned
redcraftHybridH3Krea2dual_revealULTRAV35_1146075.safetensors
20.34 GB · SafeTensor · fp8 · full
I-download
Ang mga download ay mula sa Civitai. May mga gumawa na humihingi muna ng Civitai login.
AD
I-install / Patakbuhin sa Graydient
Nangangailangan ng membership
<redcraft35-flux>
Tungkol sa model na ito
FLUX · Mga base model
Ginawa ni
AiMetatron
sa Civitai
Mga tala ng gumawa
RedCraft-红潮 Models as a Service 做好工具人 服务艺术家 Forever in memory of METAFILM Studio founder Mr. Yuan Bo 赤佬3 OCTOBER FREE 十月全免费 / NOW FREE FOR ALL 赤佬5 BUZZ Deal (K2T) 商务版 T2I生图 PayAccess 88,800 Buzz 适用于商K素材生产及相关内容生成(单独付费访问模型) Applicable to commercial production and related content generation ( model access paid separately ) For Ultra Real Chinese photoreal photography (RAW files need post-processing) 適用於Ultra Real華人寫實攝影(RAW檔需後期) 红潮H3 Hybrid 混合动力版 极速视频生成 PayAccess 888,888 Buzz 该模型 PaidAccess 包含以下所有模型(及后续更新服务) RedCraft | 红潮 | REDMIX Hybrid A2A beta2 + LTX25 2k 16-bit HDR- 08/25/2026 beta2 版本融合了 LTX2.5 distilled 作为2k高清化方案,并且消除了音频bug。 The beta2 version integrates LTX2.5 distilled as a 2K HD solution and has eliminated audio bugs. (如有问题请站内信咨询 contact us via in-site message) Dark Beast | 黑兽 H3 Director Edition 自动短剧生产线 08/28/2026 是原生H3单次采样直出2k分辨率的高清方案( 768P/VSR/RIFE TensorRT ) 所有示例短片均为 6-10 步 黑兽 H3 modified 版本单次采样生成 REDGraft | LTX 2.5 | 老同学 Fast 2K 16bit-HD| sulphur2 ported 移植版 LTX 16 bit HDR & Nvidia RTX VSR The LogC3 transform and inverse transform are used prior and after generation (accordingly) in order to achieve the dynamic range of 16 bit within normal number range. RIFE TensorRT Frame interpolation 工作流预览: 付费用户提供一对一配置服务 One-on-one configuration services are provided to paid users. The "RedCraft" "Black Beast" and "REDGraft LTX" model series REAL-Time generation speeds of the B300 (如有问题请站内信咨询 contact us via in-site message) Online Buzz Payment & Model Access - Online Buzz payment is supported, granting direct access to the models. - Payments in fiat currency or cryptocurrency are also accepted. - Regardless of the payment method chosen, you will gain access to all of my models. - If the service configuration requires the use of third-party models, I will pay the corresponding fees to the contributors. let me know your requirements and configuration needs. Thank you! 🙏 这套方案的核心不是「一个模型一次出 2K」,而是 H3 负责低分辨率语义草稿,LTX-2.5 负责 IC 引导的画幅放大与16bit HDR输出。先把内容做对,再把分辨率做高,所以能在 16GB 级显存上相对稳定高速地出 2K 视频。 为什么要双模型 MiniMax H3 擅长「生成」 低分辨率图生视频,同时出画面和音频。提示词、镜头、人物和声音都在这一段定下来。步数少(约 6 步),分辨率低,所以草稿快、语义稳。 LTX-2.5 擅长「增强」 不重新编故事,而是把 H3 成片当 IC-LoRA 的视频引导,做 V2V。蒸馏 8 步 + 潜空间 ×2 放大 3 步,再 RIFE 插帧到 48fps、VSR 拉到约 1440×2160。画质、边缘和 2K 细节主要靠这一段。 两者互补:H3 解决「像什么、怎么动、配什么声」;LTX 解决「够不够清、够不够 2K」。全程按原视频约束,比单模型直接冲 2K 更稳,也不容易跑偏。 效率从哪来 - 先低后高:贵的 22B 级计算主要花在中分辨率 V2V,而不是从噪声直接出 2K。 - 蒸馏 + 手动 sigma:LTX 侧大约 8+3 步,比全量采样短很多;自定义 sigma 用来压住细节,而不是靠加步数硬堆。 - 模型体积可控:H3 用 int8 剪枝包,LTX 用 22B 裁切版,再加 IC spatial upscaler,而不是上完整大包。 - 音频复用:声音在 H3 阶段生成,LTX 只做参考和同步,不必再跑一遍文生音频。 结果是:草稿快、放大可控、最终 2K 输出相对稳定。 显存怎么看 显存预期 16GB 及以上 按当前参数可跑:H3 草稿 + LTX IC V2V + 2K 输出。这是这套方案的设计档位。 低于 16GB 能跑,但要接受更慢(更多卸载、tile、CPU 换算),或下调参数:分辨率、时长、IC 放大、tile、插帧档位。 低于 16GB 时,优先砍的是 LTX 分辨率和潜空间 ×2,而不是先砍 H3 的语义草稿——草稿错了,后面放大只会把错误放大。 一句话 H3 用低成本把「内容 + 声音」做稳,LTX-2.5 用 IC V2V 把「清晰度 + 2K」做上去。分工明确,所以比单模型直出 2K 更省、更稳;16GB 以上是舒适区,再往下就要用时间和画质换显存。 RedCraft Krea2 DUAL · MASO Edition RedCraft-LowNoise-MASO-MangaDrama-Krea2Turbo-RedMix-v4 RedCraft-HighNoise-MASO-MangaDrama-Krea2Turbo-RedMix-v4 这是为 RedCraft / Dark Beast / REDGraft H3 配套制作的 Krea2 DUAL 双模型混合降噪版本, 主要用于生成日本漫画风格的漫剧素材图。 DUAL 模式分别使用 HighNoise + LowNoise 模型接力采样,在高噪声阶段重新释放 Krea2 TURBO 被压制的随机多样性。 因此它不是一个追求“每次都一样听话”的 fine-tune ——抽卡、重抽、再抽,才是正确打开方式。 WF of RedCraft Krea2 DUAL 严格指令遵循不是它的强项,随机性才是。 This is not a strict prompt-following model. A Krea2 DUAL hybrid denoising model designed for RedCraft / Dark Beast / REDGraft H3, specifically tuned for Japanese manga-style visual assets and manga-drama production. DUAL uses separate HighNoise + LowNoise models throughout the sampling process, bringing back more of Krea2's high-noise stochastic diversity. It works best with IL / Pony / SD15-style Danbooru Tags, where randomness and prompt interpretation are part of the workflow. The trade-off is simple: More randomness → More cherry picking → More broken anatomy. 随机性 ↑ → 抽卡难度 ↑ → 肢体崩坏 ↑ Yes, sometimes it feels like A1111 from three years ago. But when the pull hits, the model can produce high-dynamic poses, unusual compositions and motion combinations that conventional models rarely reach. 它尤其适合使用 IL / Pony / SD15 风格的 Danbooru Tags 进行提示。 严格指令遵循不是它的强项,随机性才是。 某些时候,你会感觉自己又回到了三年前的 A1111。 但当它抽中时,能够得到一些常规模型很难产生的高动态、非常规构图与动作组合 ——这也是这个版本存在的意义。 So this is, officially: MASO Edition — 受虐狂最爱 A Masochist's Favorite 不是最听话的模型,但可能是最值得多抽几次的那个。 RedCraft | 红潮 | REDMIX Hybrid A2A beta1 众神归位 Lightning 8 - 08/13/2026 "Unlocked" versions of text-encoding models have not been shown to offer improved NSFW capabilities, and their impact on DiT models remains unclear due to the lack of alignment training. However, they can serve as upstream models for prompt enhancement and are highly beneficial for prompt optimization. 解锁版本的文本编码模型未被证明有NSFW能力的提升,并且由于缺乏对齐训练,对DIT模型的作用尚不明确。但是可以作为提示词增强前置模型,对提示词优化有很大帮助: NVFP4 (4-bit) Qwen3-VL-32B text encoder Abliterated HF Repo ( 6block/MiniMax-H3-Qwen3-VL-Abliterated-NVFP4 ) Qwen3-VL-32B INT8 TensorWise + ConvRot HF Repo ( linjian257/qwen3vl_32b_minimax_h3_int8_convrot_uncensored-by-linjian257 ) Qwen3-VL-32B Heretic (MiniMax-H3 text encoder) — NVFP4 HF Repo ( sakamakismile/Qwen3-VL-32B-Heretic-MiniMax-H3-NVFP4 ) License - MiniMax H3 is released under the . - MiniMax H3 依据 MiniMax H3 社区许可协议授权,版权所有 © 2026 MiniMax。 - This model is a fine-tuned version of MiniMax H3, with modifications to the original weights."本模型依据 MiniMax H3 社区许可协议授权" - MiniMax H3 is released under the . - MiniMax H3 依据 MiniMax H3 社区许可协议授权,版权所有 © 2026 MiniMax。 - This model is a fine-tuned version of MiniMax H3, with modifications to the original weights."本模型依据 MiniMax H3 社区许可协议授权" No Mosaics. 无码 2倍速 KREA 2 赤佬 Bastard3 Edition REDZ 2 红潮 造相2 HDEdition INT8/INT4 Convrot for ComfyUI 0.27 [Native 原生节点支持] Uploaded File name: Krea2RedMix1.1-INT8-Convrot-ComfyUI (original native) File name: Krea2RedMix2.1-INT8-Convrot-ComfyUI (no mosaics) File name: Krea2RedMix3.1-INT8/INT4-Convrot-ComfyUI (visual effects) File name: REDZ
6,163 download · 430 like sa Civitai
SHA256
4F6C426A679CBCF5C75342ECFA946C56F2D4CCC1DFBA5DED40A8AEFCD3EB5A8D
ModelTrends.ai Model ID
#16947
I-flag ang nilalaman
Mga halimbawang render
Mga prompt at setting na ibinahagi ng mga gumawa ng mga render na ito sa Civitai. Pumili ng render para makita kung paano ito ginawa.
Mga setting
Laki
2592x4608
Prompt
A candid photo of a naked 18 years old Finnish woman with small breasts, petite body and dirty long straight brunette hair standing in kitchen. (Realistic fingers:0.5). The entire room is well-lit, with no shadows obscuring her features. The background is sharp. The kitchen is dirty and there is lots of trash on the floor.
Mga setting
Sampler
DPM++ 2M
Steps
15
Guidance
3.5
Seed
1819806903
Laki
864x1536
Prompt
role play of female submission,Male POV perspective,women kneeling in front of them.The secretary sets up a video conference call between the CEO and international partners. She wears a fitted red dress, her hair styled into a neat chignon. With a wireless mouse in one hand and a remote control in the other, she ensures that the technology works seamlessly for the CEO's presentation.
Negative prompt
,nsfw
Mga setting
Laki
2592x4608
Prompt
A candid photo of a naked 18 years old Finnish woman with small breasts, petite body and dirty long straight brunette hair standing in kitchen. (Realistic fingers:0.5). The entire room is well-lit, with no shadows obscuring her features. The background is sharp. The kitchen is dirty and there is lots of trash on the floor.
Mga AI model para sa paggawa ng larawan, video at teksto
Ang redcraft35 flux ay isang base model para sa pamilyang Flux na nakalista sa ModelTrends.ai, isang read-only na catalog ng mga open source AI model para sa larawan, video at teksto. Ikumpara ito sa ibang Flux model, tingnan ang heat score nito para makita kung gaano ito kasikat, at buksan ito sa PirateDiffusion o BitVector para subukan.
Mag-browse ayon sa pamilya ng model
I-browse ang lahat ng model