ChrisColeTech/Pixal3D-GGUF

来源：🤗image-to-3dmit16 GBGGUF✓ 17 个校验和30 天前更新

评论分享想法，塑造主权 AI 的未来。

@ChrisColeTech 尚未认领使用同名 Hugging Face 账户或组织成员账户登录，以验证此用户名。认领 @ChrisColeTech

文件与来源

来源可在 🤗 获取

校验和已记录 17 个

种子未收录

节点群未检查

来源修订版本: e84fdc34a8f6…
记录时间: 2026年10月16日 00:00 UTC
权重文件: 17
模型大小: 16 GB
下载量 · 上个月: 182
发布者: 未认领

权重

16 位

bf162.7 GB
bf162.8 GB
bf162.8 GB
bf162.8 GB

其他

Weights5.0 GB
7 个文件
extras/moge-2-vitl/model.pt 1.3 GBextras/dinov3-vitl16/model.safetensors 1.2 GBsplit/decoder/shape_dec_next_dc_f16c32_fp16.safetensors 948 MBsplit/decoder/tex_dec_next_dc_f16c32_fp16.safetensors 948 MBextras/birefnet/model.safetensors 444 MBsplit/decoder/ss_dec_conv3d_16l8_fp16.safetensors 148 MBextras/naf/naf_release.pth 3 MB

Pixal3D — GGUF build

The Pixal3D image-to-3D pipeline with its three 1.3B DiTs quantized to GGUF — ≈2.7 GB each instead of ≈5.5 GB, roughly halving the download and the resident footprint. ≈85–120 s per asset on an RTX 5090, with PBR material baked into the mesh.

What this repo is: GGUF quantizations of the Pixal3D sparse-structure, shape and texture transformers, plus the fp16 decoders and the background remover / DINOv3 encoder the pipeline needs — weights only, not a retrain. Every sample below was generated with these exact GGUF weights.

Samples

Single image in, textured mesh out. Source images were rendered with Z-Image Turbo; the meshes are Blender Workbench renders of the raw .glb — no cleanup, no retopology, no separate paint stage.


_{source — `a cute chunky retro robot toy standing upright, rounded metal body, simple friendly face, studio product photograph on a plain white background`}	_{mesh — 17.1 MB `.glb`, generated in 119 s, seed 42}

_{source — `an ornate ceramic teapot with a curved spout and handle, glazed blue and white porcelain, studio product photograph`}	_{mesh — 15.5 MB `.glb`, generated in 85 s, seed 42}

Turntable

Four views, 90° apart.

The chest display and dial, the ear knobs and the boot flare all survive quantization, and the surface reads as brushed metal — material is produced with the geometry rather than in a later pass.

Recommended settings

Parameter	Production value	Meaning
`seed`	any	Deterministic per seed
input	one RGB(A) image	Centred subject, plain background
output	`.glb`	Mesh with baked material

Supported modes: img2mesh, txt2mesh, and the _textured variants

Notes and gotchas

⚠ Meshes export rotated 180° relative to some other generators. Pixal3D puts the subject's front along the opposite axis from TripoSG/TRELLIS.2, so a fixed camera that frames those correctly renders Pixal3D output from behind. Orbit the camera 180°, or check one contact sheet per model before trusting a shared preset.
Material comes for free — no separate paint stage, which is the main reason to pick this over a geometry-only model.
Loads in a low-VRAM mode by default, reporting ≈0 GiB resident after load and streaming weights in as it runs. Generation still wants the card largely to itself.
Two shape DiTs ship here — _512_ and _1024_, differing in latent resolution. Both are the same 1.3B architecture; pick one.
Sparse-conv backend — logs [SPARSE] Conv backend: flex_gemm; Attention backend: flash_attn on load and pulls a valeoai/NAF estimator from torch.hub on first run, so a fresh machine needs network access.

Files

Path	Size	Role
`split/shape/slat_flow_img2shape_dit_1_3B_1024_bf16.gguf`	2.78 GB	shape DiT, 1024 latents
`split/shape/slat_flow_img2shape_dit_1_3B_512_bf16.gguf`	2.78 GB	shape DiT, 512 latents
`split/texture/slat_flow_imgshape2tex_dit_1_3B_1024_bf16.gguf`	2.78 GB	texture DiT
`split/Sparse/ss_flow_img_dit_1_3B_64_bf16.gguf`	2.68 GB	sparse-structure DiT
`split/decoder/shape_dec_next_dc_f16c32_fp16.safetensors`	948 MB	shape decoder (fp16, not quantized)
`split/decoder/tex_dec_next_dc_f16c32_fp16.safetensors`	948 MB	texture decoder (fp16)
`split/decoder/ss_dec_conv3d_16l8_fp16.safetensors`	148 MB	sparse-structure decoder (fp16)
`extras/dinov3-vitl16/`	1.21 GB	DINOv3 image encoder
`extras/birefnet/`	444 MB	background remover
`extras/moge-2-vitl/`	1.31 GB	geometry estimator

Provenance

Upstream base model: Pixal3D (TencentARC). Full-precision safetensors of the same weights live in ChrisColeTech/Pixal3D.
This build: GGUF quantizations of the three transformers; decoders and extras are unquantized. Weights are not retrained here.
License: MIT, per upstream.


_{source — `a cute chunky retro robot toy standing upright, rounded metal body, simple friendly face, studio product photograph on a plain white background`}	_{mesh — 17.1 MB `.glb`, generated in 119 s, seed 42}

_{source — `an ornate ceramic teapot with a curved spout and handle, glazed blue and white porcelain, studio product photograph`}	_{mesh — 15.5 MB `.glb`, generated in 85 s, seed 42}