<a rel="ugc" href="https://ko-fi.com/janxd"><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/b9fba3ae-90a2-4ac0-9a2f-b812ff0182b6/original=true/b9fba3ae-90a2-4ac0-9a2f-b812ff0182b6.jpeg" /> </a>👉 Join me on <a target="_blank" rel="ugc" href="https://discord.gg/tWrKk3jcXx">our discord server</a> (<a target="_blank" rel="ugc" href="https://discord.gg/tWrKk3jcXx">https://discord.gg/tWrKk3jcXx</a>)! Share art, ask for help, or just chat. We have <a target="_blank" rel="ugc" href="https://civarchive.com/articles/13331/7k-followers-updates-and-civchan-bot-launch">CivChan bot plus games</a> there!👉 Support future updates: <a target="_blank" rel="ugc" href="https://ko-fi.com/janxd">Buy me a coffee </a>or tip buzz! Every bit helps. Thank you for your support!<hr /><h3 id="janima-is-a-highquality-texttoimage-model-finetuned-from-animabasev1.0-a-2bparameter-animefocused-diffusion-model-created-by-circlestone-labs-and-comfy-org.this-checkpoint-aims-to-keep-anima's-flexibility-for-anime-and-stylized-illustration-while-pushing-sharper-details-cleaner-anatomy-and-more-coherent-compositions-out-of-the-box."> JANIMA is a high‑quality text‑to‑image model finetuned from anima‑base‑v1.0, a 2B‑parameter anime‑focused diffusion model created by CircleStone Labs and Comfy Org. This checkpoint aims to keep Anima’s flexibility for anime and stylized illustration while pushing sharper details, cleaner anatomy, and more coherent compositions out of the box.</h3>JANIMA is designed for:<ul><li>High‑detail anime characters and illustrations</li><li>Clean linework with crisp eyes and facial features</li><li>Richer backgrounds and small object details without heavy post‑processing</li><li>General anime/stylized art (not photorealistic/realism work)</li></ul><hr /><h2 id="model-behavior">Model behavior</h2><ul><li>Inherits Anima’s strengths for anime and other non‑photorealistic content; realism is still not its main target.</li><li>Tends to produce more refined edges, textures, and micro‑details at the same resolution and steps compared to the base.</li><li>Works well as a “base” to stack LoRAs and style adapters on top, since it does not force a single over‑fitted style.</li></ul><hr /><h2 id="installing">Installing</h2><ul><li>JANIMA_v1.safetensors goes in ComfyUI/models/diffusion_models</li><li>qwen_3_06b_base.safetensors goes in ComfyUI/models/text_encoders</li><li>qwen_image_vae.safetensors goes in ComfyUI/models/vae</li></ul><hr /><h2 id="recommended-settings">Recommended settings</h2>These are good starting points; adjust per your workflow and hardware:<ul><li>Sampler: <code>er_sde</code> or similar modern sampler optimized for Anima‑based checkpoints</li><li>CFG: around 5 (you can push slightly higher or lower depending on prompt strength)</li><li>Steps: 24–30 (add more steps up to 50 if you are not planning to hi-res and upscale)</li></ul>Resolution: 512 - 1536 ^ 2 resolution supported.<hr /><h2 id="quality-tags-(optional)">Quality tags (optional)</h2>You can prepend your prompts with quality tags like:<pre><code>masterpiece, highres, absurdres, newest, best quality, score_7</code></pre>These help bias the model toward cleaner, higher‑effort outputs.<hr /><h2 id="suggested-negative-prompt">Suggested negative prompt</h2>A solid general‑purpose negative prompt for JANIMA:<pre><code>worst quality, low quality, lowres, score_1, score_2, score_3, blurry, jpeg artifacts, , long fingers, sepia, bad anatomy, missing fingers, watermark, artist name</code></pre>Tweak as needed.<hr /><h2 id="helpful-resources">Helpful Resources</h2>To get the most out of JANIMA and the Anima framework, the following community resources are highly recommended:<ul><li>Recommended ComfyUI Workflow: <a target="_blank" rel="ugc" href="https://civarchive.com/models/2426853/anima-preview-workflow">Anima Preview Workflow on Civitai</a></li><li>Style Reference: <a target="_blank" rel="ugc" href="https://anima.mooshieblob.com/">Anima Style Explorer</a> – A visual database of over 40,000 artist tags and weights recognized by the Anima model.</li><li>Character &amp; Tag Guide: <a target="_blank" rel="ugc" href="https://animadex.net/">Animadex</a> – A comprehensive list of characters and tags with visual examples optimized for Anima generation.</li></ul><hr /><h2 id="notes">Notes</h2><ul><li>Best suited for anime and stylized illustration workflows (ComfyUI or similar) using the Anima ecosystem.</li><li>All preview images are raw model outputs (no over‑editing), so you can see what JANIMA actually does at reasonable settings.</li></ul>

✨ JANIMA - Anima ✨

Merged with 2.9B new layers and maintaining the new knowledge from 2.9B.

qwen_image_vae.safetensors

Files with SHA256: fa9951492a72a39ad64c5dcbaeb75397a5258d90dd591dcef11a41d2b4aa236f