This is an experimental merged checkpoint based on Anima-Base v1.0.The model was created by merging Anima-Base with my own trained LoKR / LoRA weights, and also includes additional merged influence from hinaAnima2_R_Tweaker_v3.The inclusion of hinaAnima2_R_Tweaker_v3 has been permitted by the original R Tweaker creator.This is not an official Anima release, not a from-scratch base model, and not a standalone LoRA. It should be treated as an experimental derivative checkpoint based on Anima.<h2 id="model-overview">Model overview</h2><ul><li>Type: Checkpoint / merged checkpoint</li><li>Base model: Anima-Base v1.0</li><li>Components:<ul><li>Anima-Base v1.0</li><li>personally trained LoKR / LoRA weights</li><li>hinaAnima2_R_Tweaker_v3 merged into the checkpoint with permission from the original R Tweaker creator</li></ul></li><li>Main focus:<ul><li>anime illustration</li><li>mixed anime style</li><li>character-oriented generation</li><li>experimental merge behavior</li><li>possible partial 2.5D / depth-oriented rendering depending on prompt wording</li></ul></li><li>Trigger word: No dedicated trigger word required</li></ul>You can use descriptive prompts, Danbooru-style tags, or a mix of both.Because hinaAnima2_R_Tweaker_v3 is already merged into this checkpoint, loading it again is not required unless you intentionally want to amplify its effect.<h2 id="version-notes">Version notes</h2><h3 id="v005-unturbo">v005 unturbo</h3>This version explores a non-turbo / unturbo checkpoint direction based on Anima-Base.The goal is to preserve the flexibility of Anima while adding my own trained style and character tendencies through LoKR / LoRA merging. The final checkpoint also includes additional R Tweaker v3 influence, which may help push the output toward a more dimensional anime style depending on the prompt.Compared with a normal LoRA workflow, this checkpoint is intended to provide a more direct merged output without requiring a separate LoRA weight setting.Expected behavior:<ul><li>anime-style illustration output</li><li>flexible prompt response</li><li>stronger personal mixed-style tendency than the original base</li><li>usable with both tag-based and natural language prompts</li><li>may show partial 2.5D / semi-realistic anime behavior depending on prompt wording</li></ul><h2 id="recommended-settings-without-turbo-lora">Recommended settings without Turbo LoRA</h2>Use these settings if you want to run the checkpoint directly without Anima Turbo LoRA.<ul><li>Sampler: er_sde / euler_a / dpmpp_2m_sde_gpu / Res Multistep</li><li>Scheduler: Simple or SGM_Uniform</li><li>Steps: 25–50</li><li>CFG Scale: 4–5</li><li>Resolution: 512x512 to 1536x1536</li></ul>For quick testing, 25–30 steps can work. For final quality evaluation, 30–50 steps is usually safer.<h2 id="recommended-settings-with-anima-turbo-lora">Recommended settings with Anima Turbo LoRA</h2>This checkpoint can also be used together with Anima Turbo LoRA for faster generation.Recommended Turbo LoRA:<a target="_blank" rel="ugc" href="https://civarchive.com/models/2560840/anima-turbo-lora">https://civarchive.com/models/2560840/anima-turbo-lora</a>When using Anima Turbo LoRA, you should lower both CFG and step count.Suggested Turbo settings:<ul><li>Anima Turbo LoRA weight: 0.7–1.0</li><li>Steps: 8–12</li><li>CFG Scale: around 1</li><li>Sampler: Euler is a safe starting point</li><li>Scheduler: Simple or SGM_Uniform</li></ul>Do not use normal high-CFG / high-step settings together with Turbo LoRA at first. Turbo LoRA is designed for short-step and low-CFG generation.If the image becomes too overcooked, too flat, too noisy, or too unstable, reduce the Turbo LoRA weight, lower CFG, reduce steps, or simplify the prompt.<h2 id="prompt-tips">Prompt tips</h2>Start with quality and safety tags:<pre><code>masterpiece, best quality, score_7, safe, highres
</code></pre>For negative prompt, a short negative prompt is usually enough:<pre><code>worst quality, low quality, score_1, score_2, score_3, artist name
</code></pre>In many cases, adding too many negative tags may reduce variety or over-correct the image. Start simple first, then add more negative tags only when a specific issue appears.<h2 id="example-prompt-style">Example prompt style</h2><pre><code>masterpiece, best quality, score_7, safe, highres, 1girl, anime illustration, detailed eyes, soft lighting, looking at viewer, upper body, clean background
</code></pre>For more 2.5D / depth-oriented output, you can try adding terms such as:<pre><code>cinematic lighting, soft shadows, depth of field, detailed shading, semi-realistic anime style
</code></pre>For a flatter anime-style output, avoid too many realistic rendering terms and use simpler anime illustration tags.<h2 id="notes-and-limitations">Notes and limitations</h2>This is an experimental merge model. Output may vary depending on prompt length, seed, sampler, scheduler, resolution, CFG, and any additional LoRAs used.Known limitations:<ul><li>exact character outfit accuracy is not guaranteed</li><li>hands and small details may still require prompt refinement or inpainting</li><li>short prompts may produce unstable or overly generic results</li><li>text rendering is not a main strength</li><li>additional LoRAs may conflict with the merged style</li><li>using R Tweaker v3 again on top of this checkpoint may over-amplify its effect</li><li>using Turbo LoRA requires lower CFG and fewer steps than normal Anima settings</li></ul><h2 id="credits">Credits</h2>Base model:<ul><li>Anima-Base v1.0 by CircleStone Labs / Comfy Org</li></ul>Merged influence:<ul><li>my own trained LoKR / LoRA weights</li><li>hinaAnima2_R_Tweaker_v3, used with permission from the original R Tweaker creator</li></ul>Recommended optional acceleration LoRA:<ul><li>Anima Turbo LoRA</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/2560840/anima-turbo-lora">https://civarchive.com/models/2560840/anima-turbo-lora</a></li></ul><h2 id="license-and-usage">License and usage</h2>This model is based on Anima-Base v1.0 and should follow the original Anima license restrictions.Non-commercial use only.This checkpoint includes merged influence from hinaAnima2_R_Tweaker_v3, used with permission from the original R Tweaker creator.Please note that this is an independent experimental merge. It is not an official Anima release, not an official R Tweaker release, and not an official release from CircleStone Labs, Comfy Org, NVIDIA, or any original IP holder.This model is not affiliated with, endorsed by, sponsored by, or officially connected to CircleStone Labs, Comfy Org, NVIDIA, or any original IP holder.

mygoo_v005_unturbo

mygoo_v006 is an experimental MLP / Self-Attention block-merged checkpoint.It continues the mygoo_v005 direction by incorporating my self-trained mygoo/anima LoRAs,but uses MLP-only merging as the main style carrier instead of a full-layer merge.Additional MLP and Self-Attention reinforcement comes from mygooBaseSVD32,a rank-32 LoRA distilled from the difference between mygooV005Unturbo_v10 and anima_baseV10,allowing selected mygoo_v005 style and structural traits to be restored while preserving more model diversity.

Files with SHA256: cc46d3efdf47930aa742de2e1ae7203361f44e168be49718c6ef952e4b0c822d