AnimateDiff-Evolved text-to-video

Animate SD 1.5 generations with AnimateDiff motion modules.

Estimated VRAM

~6.08 GB — ⚠️ ESTIMATE (unverified real-world usage). Estimate, not a measured figure: weight-size floor = v1-5-pruned-emaonly.safetensors + mm_sd_v15_v2.ckpt (6.08 GB, sizes verified on Hugging Face/GitHub). Activations add more; ComfyUI offloading can reduce it. Source, checked 2026-10-13.

Models required

• mm_sd_v15_v2.ckpt — 1.818 GB ✅ verified 2026-10-13 (listing) · sha256 69ed0f5fef82b110aca51bcab73b21104242bc65d6ab4b8b2a2a94d31cad1bf0 → custom_nodes/.../models or models/animatediff_models
• v1-5-pruned-emaonly.safetensors — 4.265 GB ✅ verified 2026-10-13 (listing) · sha256 6ce0161689b3853acaa03779ec93eafe75a02f4ced659bee03f50797806fa2fa → models/checkpoints

Tested GPUs

No verified test reports yet.

Nodes

ADE_AnimateDiffLoaderWithContext ADE_UseEvolvedSampling KSampler VHS_VideoCombine

Common errors & fixes

Motion module not found

Place motion model in models/animatediff_models and restart. ⚠️ unverified: Fix is general guidance; not confirmed against the cited source.

Low-VRAM tips

⚠️ General guidance, not individually verified.

• Use context options (sliding window) to cap frames in memory
• Lower resolution to 512x512

Source & credit

Workflow by Kosinkadink (ComfyUI-AnimateDiff-Evolved). Get it from the original: https://github.com/Kosinkadink/ComfyUI-AnimateDiff-Evolved. License: Custom node: Apache-2.0.