Inference Time Guidance And Prompt Conditioning

via “prompt-conditioned video generation with classifier-free guidance”

text-to-video model by undefined. 89,853 downloads.

Unique: Integrates classifier-free guidance as a native parameter in the WanPipeline, allowing dynamic adjustment of guidance_scale without pipeline recompilation or model reloading. Supports both positive and negative prompt conditioning in a single forward pass architecture, reducing inference overhead compared to sequential conditioning approaches.

vs others: More efficient than training separate classifier models for prompt weighting; provides finer control than fixed-guidance alternatives while maintaining inference speed comparable to unconditional baselines.

via “inference-time guidance and prompt conditioning”

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

Unique: Implements classifier-free guidance by computing both conditional (text-guided) and unconditional predictions at inference time, then blending them via guidance scale. This allows post-hoc control of prompt adherence without model retraining, using a learned unconditional prediction head.

vs others: More flexible than fixed guidance because scale can be adjusted per-generation without retraining, and more efficient than training separate models for different guidance strengths because a single model supports the full guidance range.