V2anima-base-1 + some of my loras + official anima-turbo-lora-v0.2test in forge-neoER SDE BETAstep=4-16 prefer 6CFG=1-4 prefer 1.25offset=3-12 prefer 8The advantage of this version which is using the official Turbo Lora is that it's very fast; a 5070TI can be generated in less than 5 seconds in 6 steps, which is quite sensitive to prompts. The problem is that because it's generated so quickly, it's not sensitive to seed changes, and the output is almost the same with same prompt.V1anima-base-1 + some of my loras + Cosmos-Predict2.5-2B-base-distilled-LoRAtest in forge-neoER SDE BETAstep=8-16 prefer 12CFG=1-6 prefer 4offset=3-6 prefer 4

Files with SHA256: b033754e0814735603b963b7cfb8f08c894da0c322384de3d88a00737fdf03e7