This LoRA was trained with AI Toolkit.To use this AI Toolkit Krea 2 Edit LoRA in ComfyUI, install Ostris's custom node pack:ComfyUI-Krea2-Ostris-Edit<a target="_blank" rel="ugc" href="https://github.com/ostris/ComfyUI-Krea2-Ostris-Edit">https://github.com/ostris/ComfyUI-Krea2-Ostris-Edit</a> This LoRA was trained with KV Cache enabled in AI Toolkit. When using it in ComfyUI, set <code>kv_cache</code> to ON in the <code>Krea 2 Ostris Edit Model Patch</code> node.Using the example workflow with KV cache enablingPrompt 1 – Natural photorealistic conversionConvert the anime image into a natural photorealistic live-action photograph while preserving the exact subject count, age category, identity-defining features, pose, composition, clothing, objects, background, lighting, and colors.```Prompt 2 – High-end Cosplayer conversionConvert the anime image into a premium high-end cosplay photograph of clearly adult cosplayers with polished beauty retouching, refined social-media filtering, cinematic color grading, realistic skin and fabric, while preserving the exact subject count, pose, composition, character features, costume design, objects, background, lighting, and colors.H3 Anime-to-Live-Action LoRA (Experimental)An experimental style-transfer LoRA built on H3, designed to transform anime-style video sequences into realistic live-action footage.Important Usage Notes<ul><li>Pair with Video Captioning (Recommended):For best results, pair this LoRA with a video-captioning model (VLM) or provide a thorough description of every camera cut and shot transition in your prompt.</li><li>Multi-Shot Limitation:If the prompt only covers a single frame or misses subsequent cuts, the LoRA may only apply the live-action conversion to the first shot (or the first two shots), failing to stylize later scenes.</li><li>You may need to use an audio refiner node to fix the audio</li></ul>Tested Environments<ul><li>Native H3 Base Model: Fully tested and verified.</li><li>H3 + Accelerated / Lightning LoRAs: Tested and verified; maintains style consistency even under fast, low-step setups.</li></ul>Recommended Workflow<ol><li>Captioning: Run your source anime clip through a video VLM to extract a full description covering scene transitions and camera dynamics.</li><li>Prompt Setup: Structure your prompt to account for every cut (e.g., <code>Shot 1: ... -&gt; Cut to Shot 2: ...</code>)</li></ol>

Anime to Realism

H3 Anime-to-Live-Action LoRA (Experimental)An experimental style-transfer LoRA built on H3, designed to transform anime-style video sequences into realistic live-action footage.Important Usage Notes<ul><li>Pair with Video Captioning (Recommended):For best results, pair this LoRA with a video-captioning model (VLM) or provide a thorough description of every camera cut and shot transition in your prompt.</li><li>Multi-Shot Limitation:If the prompt only covers a single frame or misses subsequent cuts, the LoRA may only apply the live-action conversion to the first shot (or the first two shots), failing to stylize later scenes.</li><li>You may need to use an audio refiner node to fix the audio</li></ul>Tested Environments<ul><li>Native H3 Base Model: Fully tested and verified.</li><li>H3 + Accelerated / Lightning LoRAs: Tested and verified; maintains style consistency even under fast, low-step setups.</li></ul>Recommended Workflow<ol><li>Captioning: Run your source anime clip through a video VLM to extract a full description covering scene transitions and camera dynamics.</li><li>Prompt Setup: Structure your prompt to account for every cut (e.g., <code>Shot 1: ... -&gt; Cut to Shot 2: ...</code>)</li></ol>

Files with SHA256: 7dc148d69ec4c4a586bcb8de1c263072a66977c67cf849d4f25c4a6b75946b39