JoyFox-Qwen3.6-35B-A3B-RP-Aggressive is designed for sustained character voice, direct instruction following, coherent scene continuation, low role-break frequency, and long-context creative dialogue. It combines roleplay supervised fine-tuning, preference optimization, explicit response-length control, and a final activation-space refusal-direction intervention. The model retains the original Qwen3.6 multimodal architecture, 262K native context, Mixture-of-Experts routing, and native Multi-Token Prediction head. The Aggressive variant applies the stronger form of the refusal-direction intervention. It is intended to answer directly instead of falling into repetitive policy-style refusals, prematurely ending a scene, or breaking character. “Aggressive” describes the strength of the behavioral intervention, not the model's personality or default writing tone.
Explore AI models 11
JoyFox-Reverie-27B
joyfox基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
LTX-2.3-Transition-LORA
joyfoxThis LoRA is trained on top of **Lightricks/LTX-2.3** and is built with a custom training paradigm tailored for high-consistency video generation. It was originally optimized for **first-frame / last-frame guided transition videos**, but the same training strategy also gives it strong generalization in: - **First-to-last frame video generation** - **Text-to-video** - **Image-to-video** - **Stylized transformation and scene transition generation**
LTX2.3-ICEdit-Insight
joyfox**LTX2.3-ICEdit-Insight** is a task-aware video restoration and editing model family developed by **JoyFox Lab**, built on top of the **LTX-2.3 DiT-based audio-video foundation model**. - **Video Restoration**: degradation recovery, compression cleanup, blur and noise reduction, and damaged detail restoration. - **Video HD Enhancement**: super-resolution, detail reconstruction, texture sharpening, and perceptual quality improvement. - **Watermark Removal**: logo cleanup, semi-transparent overlay removal, and occlusion-aware background reconstruction. - **Subtitle Removal**: hard subtitle removal, caption cleanup, text overlay removal, and temporally stable inpainting. Unlike conventional frame-level enhancement pipelines, this model family operates as a **generative video restoration system** in latent video space. It is designed to preserve global structure, camera motion, object identity, and temporal consistency while reconstructing missing or degraded visual content.
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
This is a model for High-definition magnification of the picture, trained on , and it is mainly used for losslessly enlarging images to approximately 2K size.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
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Qwen-Image-Edit-MeiTu
joyfox基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
This release focuses on reducing false refusals and unnecessary policy-style preambles while retaining the native architecture and general capabilities of `Qwen/Qwen3.8-27B`. The final checkpoint preserves the official tokenizer, chat template, and configuration, the complete vision stack and multimodal projector, native Multi-Token Prediction (MTP) weights. Vision tensors remain unchanged and are verified separately. MTP tensors remain unchanged and are verified separately. “Aggressive” describes the strength of the low-overrefusal behavior. The intended response style is direct and substantive for benign, fictional, analytical, educational, authorized, privacy-respecting, or otherwise legitimate requests, including requests whose wording is sensitive or ambiguous.
Wan2.1-Fight-LoRA
joyfox基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
No matching models
Adjust provider, category or input/output filters. New models are added continuously.
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
Compares base text-token rates within the same channel
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
Understand before you choose
How should API prices be compared?+
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Do open weights mean free commercial use?+
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Is the top-ranked model the best for me?+
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.