DreamX-Creator 1.0 on ZeroGPU: vendored videox_fun + dreamx_inference from AMAP-ML upstream; generate(image, prompt)->(mp4, last-frame PNG, seed), neutral keyframe when image empty, DREAMX_CKPT_DIR for persistent checkpoints, diffusers 0.37.1 stack

Resolve dep graph: transformers 5.16.1 (needs hub>=1.23) + numpy 2.1.3 for torch 2.6

diffusers 0.40: load LTX2 GGUF via LTX2VideoTransformer3DModel.from_single_file

Fix GGUFQuantizationConfig import + pin diffusers 0.33 (LTX2 + GGUF)

Replace with LTX-2.5 Docker Space app (text_to_video / i2v + narration audio)

add files