encoder

Ready · Qwen3-VL conditioner, bfloat16, unquantized, 64 decoder layers, read at layer 50 · loaded in 206s · repo hf22ur/clip-text

Prompt

First keyframe (optional)

Last keyframe (optional)

Canvas

num_frames (17n + 5)

Rewrite the prompt into the trained format first (adds ~15-50s)

prompt_embeds + text_token_tags (safetensors)

Resolved plan