<h2 id="generation-(recommendation)">Generation (Recommendation)</h2><ul><li>Nomal Model Generation (Recommendation)<ul><li>Sampler: dpmpp_2m/Euler/Res-multistep/Er-sde</li><li>Scheduler: sgm-uniform/beta/beta57/linear-quadratic</li><li>Resolution: 832x1216, 812x1216, 1152x1536, 1536x1536 (iffy)</li><li>Steps: 28-50</li><li>CFG: 3.5-5</li></ul></li></ul><ul><li>Turbo Model Generation (Recommendation)<ul><li>Sampler: Er-sde/dpmpp_2m_sde_gpu</li><li>Scheduler: simple/sgm-uniform</li><li>Resolution: 832x1216, 812x1216, 1152x1536, 1536x1536</li><li>Steps: 12</li><li>CFG: 1 </li></ul></li></ul> This model is a merge I created by testing various combinations of LoRAs—a process that involved a lot of experimentation. I don’t recall the exact combinations, but I used the "<a target="_blank" rel="ugc" href="https://github.com/shootthesound/comfyui-model-diff-to-lora">comfyui-model-diff-to-lora</a>" tool alongside the "Anima 1.0 base 2B" model. I extracted LoRAs by setting the original, unmodified base model as "model 1" and the model containing all the desired LoRA combinations as "model 2." The final output was a 700MB, rank-256 LoRA; given my PC’s specs, the extraction process takes about 15 minutes.After combining and extracting the LoRAs using this custom node, I used "<a target="_blank" rel="ugc" href="https://github.com/shin131002/ComfyUI-Anima-Remap">ComfyUI-Anima-Remap</a>" to adapt the LoRAs from the "Anima 2B" version to the "Anima 2.9B" version. I then saved these adjustments, resulting in customized versions of both the Anima 2B and 2.9B models, available in fp16 and int8 formats.I also extracted a "turbo" LoRA from the "Anima 1.0 turbo" model.Using "comfyui-model-diff-to-lora," I set "Anima 1.0 base" as "model 1" and "Anima 1.0 turbo" as "model 2" to perform the extraction.Note: I did this because I noticed that the "anima-turbo-lora-v0.2.safetensors" file they provide offers lower quality than what is already baked into the turbo models themselves. By using "comfyui-model-diff-to-lora," I was able to isolate and extract the specific differences between the models. I also extracted a LoRA from "anima_aestheticV11," which works perfectly without needing to download a separate version of the model. Note that LoRAs can be extracted at ranks 256, 128, 64, 32, 16, and 8;the memory requirement is essentially halved with each step down in rank.<a target="_blank" rel="ugc" href="https://github.com/shootthesound/comfyui-model-diff-to-lora">https://github.com/shootthesound/comfyui-model-diff-to-lora</a><a target="_blank" rel="ugc" href="https://github.com/shin131002/ComfyUI-Anima-Remap">https://github.com/shin131002/ComfyUI-Anima-Remap</a>Specs:Xeon E5 2650v4, 16GB RAMRX 7600 8GB240GB SATA SSD

Anima 2B & Anima 2.9B Flat Style Boost [Normal/Turbo] int8 - fp16

Meger_hdrVAEAnimaQWENImage.safetensors

Files with SHA256: 7e1a408d6e79612b6038e7a55b1423b2be3ec071985d816483dad88ba29147aa