ChenkinNoob-XL-V0.2

Overview

ChenkinNoob is an independent open-source team continuing the noobai-XL-1.1 lineage. Version 0.2 officially released on 2025-12-25 and keeps the familiar high-quality aesthetics while integrating newer Danbooru data (extended through 2025-11-23). Internal evaluations show noticeable gains over V0.1 in character consistency, detail rendition, and prompt fidelity.

Model Introduction

Model Details

• Developed by: ChenkinNoob team
• Model Type: Diffusion-based text-to-image generative model
• Fine-tuned from: Laxhar/noobai-XL-1.1
• Sponsored by: 极逸 SOON (soonjy.com)
• Independence Statement: The ChenkinNoob team operates independently; this release is not an official Laxhar Lab product but inherits their open-source foundations.

Communication

QQ Groups: : 425395454

Discord: https://discord.gg/jzwzwyCKZ4

Version Highlights

• Base Model: fine-tuned from Laxhar/noobai-XL-1.1 with ChenkinNoob training recipes.
• Dataset Refresh: incorporates the latest Danbooru samples up to 2025-11-23 for more contemporary subjects and trends.
• Quality Focus: preserves the “noob” visual DNA—clean composition, appealing palettes, and strong anatomy—while improving edge cases (hands, accessories, layered outfits).
• Open Release: model weights and training notes remain under the same fair-ai-public-license-1.0-sd terms.

Recommended Use

• CFG: 5–6
• Steps: 25–30
• Sampler: Euler a (or comparable high-frequency samplers)
• Resolution: total area ≈ 1024×1024 (768×1344, 832×1216, 896×1152, 1024×1024, 1152×896, 1216×832, 1344×768)
• Positive Prompt Seeds: high resolution, aesthetic, excellent, medium resolution, year 2025, newest
• Negative Prompt Seeds: low resolution, e621, Furry, old

New Tags in V0.2

Tag Type	Label	Definition
Resolution	High Resolution	Image area ≥ 2048 px
	Medium Resolution	1024 px < image area < 2048 px
	Low Resolution	Image area ≤ 1024 px
Aesthetic	Esthetic	Among the top 100k most liked posts on Danbooru
	Excellent	Among the top 1M most liked posts on Danbooru
Era	Year YYYY	Explicit year tags such as year 2025
	Range: Newest	Combined label for 2022–2025 content
	Range: Old	Combined label for 2018 and earlier

Roadmap

ChenkinNoob-XL-V0.2 (Released: 2025-12-25)

• Release package includes refreshed prompts, negative prompts, and example workflows.
• Ship notes detail the quantitative improvements over V0.1 plus recommended fine-tuning hooks for downstream creators.

ChenkinNoob-XL-V0.3 (ETA: January 2026)

• Focused on further stability, inference efficiency, and better LoRA compatibility.
• Rolling preview builds will be shared with the Discord closed-beta group ahead of public release.

Anime-focused SDXL All-in-one ControlNet

• Dedicated ControlNet designed for anime workflows (pose, layout, coarse shading) will ship alongside the ChenkinNoob-XL 1.0 stable release or the first production-ready milestone that meets quality gates.
• Development updates will be posted independently from the base model checkpoints so adopters can plan pipeline integrations.

Participants and Contributors

Participants

• Chenkin: Civitai | Huggingface
• waww: Huggingface
• leafmoone: Huggingface
• heathcliff: Huggingface
• tairitus: Huggingface
• Ryan Corwin: Huggingface

Contributors

• Special Thanks (Technical Support): @chinoll (Huggingface | GitHub) for providing long-term technical support and engineering assistance to the ChenkinNoob team.
• Technical Advisors (Laxhar Lab): Special thanks to @LAX (LAX) and @Nebulae (Nebulae) from Laxhar Lab for serving as long-term advisors and providing continuous guidance on model design and training.
• Art Promotion Guidance: MLiang, BLACKDUO, Sdwang, MIZhizhi
• Cover Design (V0.1): poi, neko, MMX and others
• Promotional Video Production: 米豆粒, 衡鲍, 娜拉普 SenSen
• AngelBottomless: Heartfelt thanks to AngelBottomless, core contributor to the Illustrious series, for gifting the open-source community with a stellar foundation, sharing actionable guidance with the Chenkin team, and empowering ChenkinNoob-XL to grow. Wishing continuous success and joyful days ahead!
• DeepGHS: Thanks to the deepghs team (founded by narugo1992) for open-sourcing various training sets, image processing tools, and models.
• Onommai: Thanks to OnommAI for open-sourcing a powerful base model.
• Mikubill: Thanks to Mikubill for the Naifu trainer.
• Community: Thanks to yiyi, 双月丸‖soutsukimaru, 天满, Seina_, 448, SenSen, 古川本铺, storyaura, M1nYue, Deta_DT, sheenderwn, MLiang, Sdwang, BLACKDUO, 杏仁豆腐, 孤辰, 砚青 and others for providing cover art and promotional assets used throughout the campaign, and thanks to all group members for participating in the model's closed beta testing.

V0.2 Contributors

• Cover Art Providers (V0.2): poi, Sdwang, freewill, 一费白色人种, 十一, wa我我, 屋檐铃兰448, 11.7suki, 曾青 等
• Discord Closed Beta Reviewers (V0.2) (listed by join order): NukeA.I, 6DammK9, Talan, Ryusho, NAMAME, Anzhc, Ly, HyperClap, itterative, Chat Errꙫr, rred, Bluvoll, Void, Mirai, 𝕮𝖔𝖈𝖔𝕶𝖔𝖐𝖔 (dvxdvxdv). Your skill, passion, and fearless feedback make you the backbone of this open-source community—thank you for every priceless note that keeps the iterations moving forward.