ChenkinNoob/ChenkinNoob-XL-V0.2

ChenkinNoob-XL-V0.1

Overview

ChenkinNoob is an independent open-source team continuing the noobai-XL-1.1 lineage. Version 0.2 is scheduled for release in late December 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.

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)

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	Aesthetic Tags	Expanded descriptors capturing style preference ranges introduced in V0.2
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 (ETA: late December)

• Final validation pass in progress; release package will include updated prompts, negative prompts, and example workflows.
• Ship notes will cover the quantitative improvements over V0.1 plus recommended fine-tuning hooks for downstream creators.

ChenkinNoob-XL-V0.3 (ETA: late December or early January)

• Bundles the first anime-focused SDXL all-in-one ControlNet, enabling pose, layout, and coarse shading guidance in a single checkpoint.
• Launch date depends on ControlNet development progress; milestones will be shared as soon as the feature set stabilizes.