mirror of
https://github.com/comfyanonymous/ComfyUI.git
synced 2026-06-24 00:39:30 +08:00
01a8783bee
Cube3D is an autoregressive VQ-token shape model (DualStreamRoformer) plus a VQ-VAE shape tokenizer (OneDAutoEncoder), not a diffusion model. It is wired natively following the Causal-WAN AR-video pattern: the GPT loads as a normal MODEL and generation runs through a dedicated 'cube' sampler instead of KSampler. - comfy/ldm/cube/gpt.py: DualStreamRoformer port (dual-stream RoPE attention, per-head RMSNorm, SwiGLU, KV cache; rope_theta=10000). - comfy/ldm/cube/vae.py: OneDAutoEncoder decode path (codebook lookup, decoder, occupancy decoder, dense-grid extraction + skimage marching cubes). - model_detection/supported_models/model_base: register shape_gpt as Cube3D MODEL (dims inferred from state dict; apply_model guarded to point at SamplerCube). - sd.py: detect shape_tokenizer and build CubeShapeVAE. - k_diffusion/sampling.py: sample_cube autoregressive sampler (decaying CFG + optional top-p), faithful to upstream Engine.run_gpt. - comfy_extras/nodes_cube.py: EmptyCubeLatent, CubeCodebookPatch (inject VQ codebook into wte), SamplerCube, VAEDecodeCube (-> MESH). Reuses CLIP-L conditioning, CFGGuider/SamplerCustomAdvanced, and SaveGLB. Amp-Thread-ID: https://ampcode.com/threads/T-019ec361-addb-70d8-a74b-438ce8a1e096 Co-authored-by: Amp <amp@ampcode.com> |
||
|---|---|---|
| .. | ||
| ace | ||
| anima | ||
| audio | ||
| aura | ||
| cascade | ||
| chroma | ||
| chroma_radiance | ||
| cogvideo | ||
| cosmos | ||
| cube | ||
| depth_anything_3 | ||
| ernie | ||
| flux | ||
| genmo | ||
| hidream | ||
| hidream_o1 | ||
| hunyuan3d | ||
| hunyuan3dv2_1 | ||
| hunyuan_video | ||
| hydit | ||
| ideogram4 | ||
| kandinsky5 | ||
| lens | ||
| lightricks | ||
| lumina | ||
| mmaudio/vae | ||
| models | ||
| modules | ||
| moge | ||
| omnigen | ||
| pixart | ||
| pixeldit | ||
| qwen_image | ||
| rt_detr | ||
| sam3 | ||
| supir | ||
| triposplat | ||
| wan | ||
| colormap.py | ||
| common_dit.py | ||
| util.py | ||