Two and a half weeks after MOSS-Image's debut, Civitai listings reached 1,790 entries despite unchanged official weights. An overview of checkpoints, acceleration and edit LoRAs, and ComfyUI workflows.
Tested SnapRef v1b for Anima across Base, Aesthetic, Turbo, and 2.9B models on M1 Max 64GB. Checked differences with v1a and FP8, strength, ref_guidance, two characters, multi-reference, 3D pose integration, and known README limits.
The five official Anima setups took about 38 s (Turbo) and 260 s (Base) per image on an M1 Max 64GB. Under the same conditions on an EVO-X2 (Radeon 8060S, ROCm, Windows, ComfyUI), they took about 9 s and 65 s once loaded, and a character LoRA did not change those times.
Benchmarked Anima Ref Adapter v2 and Role-Ref-KV on M1 Max across Base, Aesthetic, Turbo, and 2.9B. Tested character consistency, generation speed, and whether CharRef-LLLite can pair with Role-Ref-KV for pose control.
Tested Anima Ref Adapter on Turbo v1.0, Turbo v1.1, Aesthetic v1.1, and Anima-2.9B using ComfyUI on an M1 Max Mac. Explored what caused the 2x2 grid artifacts on Turbo and how to avoid them.
OpenAI and Anthropic published refutations of the Exponential Time Hypothesis (ETH) within hours of each other on October 26, 2026. Here is an analysis verifying the 2^o(n) complexity bounds in SymPy, the gap between Lean proofs and paper claims, why practical solvers remain unaffected, and impacts on SETH and cryptography.
Nova Anime AM, CottonAnima, AMIXA2.9B, and JANIMA 2.9B tested on an M1 Max 64GB in ComfyUI with an Anima-Base character LoRA remapped to 40 blocks. All four kept the hairstyles, but Kei's red ribbon tie turned navy in portraits. Also compares default style, background density, i2i, and speed.
I ran the latest 2B versions (as of October 21) of Hikari, AnimaIka, Hotaru Blend, Cat Tower, CapAnima, RDBT, and AnimaYume in ComfyUI on an M1 Max 64GB, using the same prompts, seed, and character LoRA as Anima-Base v1.0. All seven got the hairstyles right, but only RDBT kept Kei's ribbon tie red in both full-body and bust shots, and RDBT turned two characters into four. Default style, background density, i2i, and generation speed are compared too.
I rechecked the latest versions of the Anima derivatives from my June list, plus Civitai's top 40 Anima checkpoints by monthly downloads, as of October 21, 2026. Which 2B models were updated, which moved to 2.9B, and why the two 3.8B models are built differently.
I compared official Anima Turbo v1.1 and Aesthetic v1.1 against Base v1.0 on an M1 Max 64GB with ComfyUI. Base-trained character LoRAs worked across all 4 seeds when specifying hair and eyes, but Aesthetic v1.1 spawned extra characters in two-character prompts and Turbo v1.0 missed ribbon colors.
A local evaluation of MOSS-Image Base and SFT on an M1 Max Mac using MPS, examining prompt behavior for character portraits, text rendering, JSON layout placement, and comparisons with earlier Qwen and Anima generations.