valiantcat

This is a model for object removal, trained on , and is suitable for object removal tasks of e-commerce images, character images, and object images.For use in . The greatest advantage of using this LORA is that it maintains the consistency of the original image without changing any parts. ComfyUI Workflow This LoRA works with a modified version of Comfy's Qwen-Image-Edit workflow . The main modification is adding a Qwen-Image-Edit LoRA node connected to the base model. See the Downloads section above for the modified workflow. There is no fixed trigger word. The specific removal prompt needs to be tested more Weights for this model are available in Safetensors format. This model was trained by the AI Laboratory of Chongqing Valiant Cat Technology Co., LTD().Business cooperation is welcome

You should use `rw360xz` to trigger the image generation. You should use `人物定在空中，相机视角围绕人物向一个方向旋转` to trigger the image generation. | 控制图1 | workflow1结果 | workflow2结果(姿态控制) | |:---:|:---:|:---:| | | | | | | | | | | | | | | | |

This model — Qwen-Image-Edit-MeiTu — is an improved variant of Qwen/Qwen-Image-Edit, built with DiT-based architecture fine-tuning to enhance visual consistency, aesthetic quality, and structural alignment in complex edits. Developed by Valiant Cat AI Lab, this version aims to further close the gap between high-fidelity semantic editing and coherent artistic rendering, achieving a more natural and professional output across a wide range of prompts and subjects. Enhanced Consistency: Utilizes DiT (Diffusion Transformer) fine-tuning to ensure structural stability between input and edited regions, maintaining global spatial coherence. Aesthetic Optimization: Trained with aesthetic discriminators and curated aesthetic score datasets, producing more pleasing colors, contrast, and light balance. Better Detail Preservation: Improved low-level reconstruction for fine details such as textures, faces, and typography. Broader Scene Adaptability: Performs well on portraits, environments, product photos, and illustrations, supporting both semantic and appearance-based editing. Below are examples of consistency and aesthetic improvement in complex editing scenarios: | Input & Output | |----------------| | | | | | | | | | | Try these prompts to explore the model’s strengths: “make the lighting soft and cinematic with better balance” “enhance the photo’s composition and maintain realism” “refine skin tone and texture consistency” “improve the global color tone and aesthetic harmony” “increase photo realism and clarity without changing content” This model works seamlessly with a modified ComfyUI Qwen-Image-Edit workflow. Just use this model in the Unet node to workflow for edit image. This model was trained and optimized by the AI Laboratory of Chongqing Valiant Cat Technology Co., LTD. Visit https://vvicat.com/ for business collaborations or research partnerships. We are hiring research engineers and creative ML practitioners at Chongqing Valiant Cat Technology Co., LTD — reach out via 📧 [email protected]

This is a model for generation of embrace and kiss images of the specified person and the specified scene, trained on , and it is mainly used to generate an image of a hug and kiss in the current scene based on two uploaded character pictures and one scene picture, while maintaining consistency between the characters and the scene.For use in . ComfyUI Workflow This LoRA works with a modified version of Comfy's Qwen/Qwen-Image-Edit-2509 workflow . The main modification is adding a Qwen/Qwen-Image-Edit-2509 LoRA node connected to the base model. See the Downloads section above for the modified workflow. There is no fixed trigger word. The specific removal prompt needs to be tested more Weights for this model are available in Safetensors format. This model was trained by the AI Laboratory of Chongqing Valiant Cat Technology Co., LTD().Business cooperation is welcome

| 真实人物原图 | 动漫角色参考 | AI生成效果 | |:---:|:---:|:---:| | | | | | | | | | | | | | | | | Qwen-Image-Edit-Cosplay LoRA 是一个基于Qwen-Image-Edit-2509图像编辑模型的微调版本，专门用于动漫角色装扮迁移任务。该模型能够将动漫人物的发型、服饰和装饰道具精准地迁移到真实人物图像上，同时保持原始人物的面部特征高度一致。 核心功能特点： - 实现从动漫到真实人物的装扮风格转换 - 保持原始人脸识别特征不变 - 支持发型、服装、配饰等多种元素的迁移 - 基于Qwen-Image-Edit-2509基础模型优化 使用以下中文提示词来激活图像生成功能： `把图2中动漫人物中的发型，服饰和装扮道具迁移到图1的真实人物，图1真实人物保持高度人脸一致性` 您可以在 模型文件页面 下载并使用这个LoRA模型。该模型兼容主流的diffusers库，便于集成到现有的AI图像生成工作流中。

Overview This LoRA is trained on the Wan2.1 14B I2V 720p model. Transform any image into a video of two people began to fight Trained on the Wan2.1 14B 720p I2V base model Consistent results across different object types Simple prompt structure that's easy to adapt Join us to generate interesting video models together to generate videos with this LoRA for free - wan2.1-fight.safetensors - LoRA Model File - wanimg2videoloraworkflow.json - Wan I2V with LoRA Workflow for ComfyUI LoRA Strength: 1.0 Embedded Guidance Scale: 6.0 Flow Shift: 5.0 Prompt Template For best results, use this prompt structure: dajia,这是[object]对打得视频，镜头拉远，保持人物不变，这两个人开始对打，两个人不断旋转，拳打脚踢，姿势像是传统武术，十分专业，两个人相互比试，打的有来有回，突然左边的人腾空跳起，保持飞在空中用腿不停踢另一个人上半身，男人被踢得一边用手阻挡女人的飞踢一边后退，镜头跟随,保持背景和人物的服装不改变。 Simply replace [object] with whatever you want to let these two people fight!

Upload a picture of a person or animal, and simply enter the trigger word to get a fisheye perspective picture of the outside of the door. It has good generalization ability. You should use `991ft3` to trigger the image generation. You should use `转换成门外猫眼视角` to trigger the image generation.

Overview This LoRA is trained on the Wan2.2-I2V-A14B model. Generate any life videos of eva through prompt Trained on the Wan2.2-I2V-A14B base model Consistent results across different object types Simple prompt structure that's easy to adapt LoRA Strength: 1.0 Embedded Guidance Scale: 1.0 Flow Shift: 8.0 Prompt Template For best results, use this prompt structure:

Upload a picture of a person and an animal, and simply enter a trigger word to get a picture of a person riding an animal. The generalization is very good. The untrained edit model generates pictures with a bad ratio between people and animals, and the person will be larger than the animal. You should use `r1d3an1ma1，人骑在动物身上` to trigger the image generation.

This is a model for generation of oil painting style, trained on , and the main purpose is to generate images in an oil painting style. Surprisingly, this oil painting style can bypass the real-person image review process of sora2.For use in . ComfyUI Workflow This LoRA works with a modified version of Comfy's Qwen-Image-Edit workflow . The main modification is adding a Qwen-Image-Edit LoRA node connected to the base model. See the Downloads section above for the modified workflow. Weights for this model are available in Safetensors format. This model was trained by the AI Laboratory of Chongqing Valiant Cat Technology Co., LTD().Business cooperation is welcome

This is a model for generation of character statues, trained on , and it is mainly used to generate a photo of the current giant figurine with oneself.For use in . ComfyUI Workflow This LoRA works with a modified version of Comfy's Qwen-Image-Edit workflow . The main modification is adding a Qwen-Image-Edit LoRA node connected to the base model. See the Downloads section above for the modified workflow. There is no fixed trigger word. The specific removal prompt needs to be tested more Weights for this model are available in Safetensors format. This model was trained by the AI Laboratory of Chongqing Valiant Cat Technology Co., LTD().Business cooperation is welcome

wan 2.1 烟雾特效变装Lora，基于14个81帧视频在wan21i2v480P基础模型上训练，一共训练4000步。 推荐权重：0.8-1.2 You should use `ywbz，烟雾特效变装` to trigger the image generation.

Overview This LoRA is trained on the Wan2.2-T2V-A14B model. Generate any life videos of eva through prompt Trained on the Wan2.2-T2V-A14B base model Consistent results across different object types Simple prompt structure that's easy to adapt LoRA Strength: 1.0 Embedded Guidance Scale: 1.0 Flow Shift: 8.0 Prompt Template For best results, use this prompt structure:

This is a model for style transfer, trained on , and it is mainly used to generate five Russian matryoshka dolls from large to small for image stylization.For use in . Weights for this model are available in Safetensors format. This model was trained by the AI Laboratory of Chongqing Valiant Cat Technology Co., LTD().Business cooperation is welcome

You should use `镜头快速拉远，人物快速分裂出三个做着相同战斗姿势的影分身，站成一排，全身一直散发着浓烈的金色能量，分身保持人物一致性，令人惊叹的视觉效果` to trigger the image generation.

This is a model for Qwen-Image in Portrait generation, trained on , and it is mainly applicable to generating pictures of various Asuka characters from Japanese anime.For use in through the following code and ,The workflow files are in the folder of this project. ComfyUI Workflow This LoRA works with a modified version of Comfy's Qwen-Image workflow . The main modification is adding a Qwen-Image LoRA node connected to the base model. See the Downloads section above for the modified workflow. Weights for this model are available in Safetensors format. This model was trained by the AI Laboratory of Chongqing Valiant Cat Technology Co., LTD().Business cooperation is welcome

This is a model for style transfer, trained on , and it is mainly used to generate male and female costumes in the ancient Chinese immortal and martial arts world, allowing people to become immortal cultivators with just one click.For use in . Weights for this model are available in Safetensors format. This model was trained by the AI Laboratory of Chongqing Valiant Cat Technology Co., LTD().Business cooperation is welcome

通过qwen edit，将一张人物肖像图片转换成充满卡通的质感的头像照片 可以直接在comfyui中使用，提示词就只用填“2davat0r,转换成2D卡通头像” 推荐权重 1.0 You should use `2davat0r` to trigger the image generation. You should use `转换成2D卡通头像` to trigger the image generation.

There is no fixed trigger word. The specific removal prompt needs to be tested more Weights for this model are available in Safetensors format. This model was trained by the AI Laboratory of Chongqing Valiant Cat Technology Co., LTD().Business cooperation is welcome

This is a model for style transfer, trained on , and it is mainly used to generate many little sculptors sculpting the scenes after the characters in this uploaded picture are animated.For use in . Weights for this model are available in Safetensors format. This model was trained by the AI Laboratory of Chongqing Valiant Cat Technology Co., LTD().Business cooperation is welcome

There is no fixed trigger word. The specific removal prompt needs to be tested more Weights for this model are available in Safetensors format. This model was trained by the AI Laboratory of Chongqing Valiant Cat Technology Co., LTD().Business cooperation is welcome

Wan 2.1 basic model cannot make animals raise their index fingers like humans. This model is designed to enable animals to raise their index fingers. The content generated using this model must not be used to offend or infringe upon others; otherwise, all responsibilities will be borne by the user. This model is an LORA model trained based on the WAN2.1 T2V 14B model. It was trained using a dataset of 20 excellent images and was trained for 3200 steps, taking a total of 3 hours. Recommendation weight: 0.6. You should use `0n3f1n9er` to trigger the image generation.

wan 2.1 哥特暗黑特效变身Lora，基于wan21i2v480p模型上训练， 推荐权重：1.0 模型使用技巧 触发词：dd6rkcc，暗黑烟雾变身 一般情况只需要“触发词+一张人物图片”即可出现完美的效果 有时候输入男生的图片变身后出现女性特征（辫子头等），可在提示词后面加上“这个男生变身，保持发型不变”，想要背景呈现黑色森林城堡可以加上“背景变成暗黑森林城堡” You should use `dd6rkcc，暗黑烟雾变身` to trigger the image generation.

Wan 2.1 小孩哥三分镜工作写真Lora，基于wan21i2v480P基础模型训练。 模型可以通过一张图片生成三个分镜，但是需要上传一个小孩/小大人在办公室的照片（一般用QwenImageEdit生成)。 推荐权重：1.0 可以在RH上运行完整的工作：runninghub workflow in https://www.runninghub.cn/post/1964871069591064577 Wan 2.1 Baby boss Working 3 shot Lora, trained based on the wan21i2v480P foundation model. The model can generate three storyboards from a single image, but it requires uploading a photo of a child/little adult in an office (usually generated using QwenImageEdit). Recommended weight: 1.0 You should use `BabyBoss3Shots，三分镜婴儿视频。分镜1：一个1岁的小总裁，在豪华的总裁办公室里，他坐在大办公桌前，审批文件。分镜2：一个1岁的小总裁，在办公室的过道像宝宝一样在走路，身高只有30厘米，身后四个不同性别的秘书一边跟着一边看着他，生怕他摔倒，有的伸出手，有的在记录工作。分镜3：一个1岁的小总裁坐在劳斯莱斯豪车的后座，优雅地喝着高脚杯里的牛奶，若有所地望向窗外的城市夜景。三个场景连续，电影感，4K画质。 ` to trigger the image generation.

This model was trained by the AI Laboratory of Chongqing Valiant Cat Technology Co., LTD().Business cooperation is welcome