<p>These are anime-style LoRAs for Qwen-image. Due to my lack of familiarity with creating LoRAs for Qwen, the time required for training, and lower-than-expected effectiveness, I'm splitting them into several LoRAs based on the style of the image and intending to use them in combination.</p><p></p><h3 id="animem1">AnimeM1</h3><p>This is a slightly cooler anime LoRA. Use it a little stronger.</p><p></p><h3 id="animel1">AnimeL1</h3><p>A very old school anime style LoRA. Unless you're aiming for an analog TV style, try using it around 0.75.</p><p></p><h3 id="animek1">AnimeK1</h3><p>This is an anime illustration style LoRA that is often seen on SDXL etc.</p><p></p><h3 id="animeu1">AnimeU1</h3><p>This is a LoRA created using experimental techniques. The theme is to see how much automatic generation of style LoRA is possible. The training is limited to about one epoch, aiming for mass production.</p><p>1.0 is too strong, so use around 0.75 as a benchmark. While not a trigger word, animeU1 can be effective in some cases.</p><p>It is intended to be used in combination with other LoRAs in the series, and to extract effective components using <a target="_blank" rel="ugc" href="https://civarchive.com/models/1941621/layered-lora-loader-for-comfyui">LayeredLoraLoader.</a></p><hr /><p></p><h3 id="am2_test">am2_test</h3><p>The first LoRA I created. Generated at Rank 16 with a miscellaneous collection of images. Resolution: 1280 dots.</p><h3 id="anime-h1">Anime-H1</h3><p>Generated at Rank 32 with a collection of clean, character-focused images with little background. Approximately 400 images were used. Resolution: 1280 dots.</p><h3 id="anime-r1">Anime-R1</h3><p>Generated at Rank 32 with images featuring relatively high line detail. 1230 images were used. Resolution: 1024 dots.</p><p></p><p>Note that while the resolution was increased during training using upscaling, the original images were still low-resolution.</p><p>Adjust the LoRA strength in conjunction with CFG scale, etc. There is no restriction on the total being 1.0 when using them in combination. In some cases, using a value of 1.5 or higher individually may be beneficial. As a general rule, if the CFG scale is high, adjust it by lowering the LoRA strength.</p><p>Example: If the amount of background information is decreasing, lower the CFG scale.</p><p>There are no trigger words, but "animeH1" or "animeR1" may be effective. Please make it clear in the prompt that the image is an anime drawing.</p>

AnimeStyle LoRAs

am2_test.safetensors

am2_test v1.0

AnimeM1 v1.0

AnimeL1 v1.0

AnimeK1 v1.0

AnimeR2 v1.0

AnimeU1 v1.0

AnimeH2 v1.0

AnimeR1 v1.0

AnimeH1 v1.0

Files with SHA256: dc6fae4d8608387aade6a3dc41674622cc2d33f2a46a50e75713955d2668c886