--- title: "Pixal3D + TRELLIS.2 in ComfyUI" description: "Turn one image into a textured 3D model with Pixal3D and TRELLIS.2 in ComfyUI. Explore examples, download GLBs, and open the workflow." canonical: https://comfy.org/pixal3d-trellis2/ lang: en index: https://comfy.org/llms.txt --- # Image to 3D Model 3D Turn a single image into a textured 3D model you can inspect, download, and continue refining on the graph. Open weights Commercial use Credit estimate before run Image to textured mesh Signed in · inputs restored — no survey, no plan picker Free runs: 5 left ## Input Choose an example Add an image before running the workflow. json ``` ``` Live from your inputs — the exact payload the API takes. Continue in Comfy Cloud Open the shared workflow to generate your own 3D model. ## Result Loading 3D preview… Drag to orbit · scroll to zoom json ``` ``` Restored your image ✓ Running the graph ksampler · queue position 1 That was your fifth free run Keep running it. Creator — $20/mo · est. Textured GLB output included Pro — $60/mo · est. ≈ 800 runs · API keys · batch queues Your graphs, seeds, history, and all five outputs stay yours — free, forever. Or run it locally: it’s open source. See all plans → Textured GLB Viking axe example output [Download GLB](https://media.comfy.org/website/pixal3d-trellis2/viking-wolf-rune-axe.glb) ## Run it your way Create a key, then make your first call with the SDK. ``` # pip install comfy-sdkimport osfrom comfy_sdk import Comfyos.environ["COMFY_BASE_URL"] = "https://cloud.comfy.org"client = Comfy(api_key=os.environ["COMFY_API_KEY"])wf = client.workflows.from_file("workflow_api.json")# Upload an asset and set it as an input to the workflowasset = client.assets.from_file("viking_wolf_rune_axe.png")asset.commit()wf.set_input("122", "image", asset)# Submit the workflow and download the outputjob = client.run(wf)out = job.get_outputs("321")[0]out.to_file("viking_wolf_rune_axe_output.glb") ``` ``` // npm install @comfyorg/sdk (Node 22+)import { Comfy } from "@comfyorg/sdk";process.env.COMFY_BASE_URL = "https://cloud.comfy.org";const client = new Comfy({ apiKey: process.env.COMFY_API_KEY });const wf = await client.workflows.fromFile("workflow_api.json");// Upload an asset and set it as an input to the workflowconst asset = await client.assets.fromFile("viking_wolf_rune_axe.png");await asset.commit();wf.setInput("122", "image", asset);// Submit the workflow and download the outputconst job = await client.run(wf);const out = job.getOutputs("321")[0];await out.toFile("viking_wolf_rune_axe_output.glb"); ``` [Create API key](https://platform.comfy.org/profile/api-keys) [API reference](https://docs.comfy.org/api-reference/v2/overview) ## Frequently asked questions Trellis.2 is Microsoft's open-source image-to-3D model, released in December 2025. It is a 4-billion-parameter model built on a compact O-Voxel structured latent representation that generates geometry and PBR materials from a single image at effective resolutions up to 1536³. It now runs natively in ComfyUI core. Pixal3D is an image-to-3D model from Tsinghua University and Tencent ARC Lab. It uses pixel-aligned generation to keep the 3D output in direct correspondence with the input view, producing near-reconstruction-level fidelity. It is built on the Trellis.2 backbone and runs natively in ComfyUI alongside it. Yes. Trellis.2's code and weights are MIT-licensed, and ComfyUI's native implementation replaces the non-commercial nvdiffrast and nvdiffrec dependencies from the original pipeline with a from-scratch PyTorch and SciPy reimplementation. There are no non-commercial dependencies in the ComfyUI pipeline, so generated assets can be used in commercial work. Pixal3D shares the Trellis.2 backbone, VAEs, and DINOv3 image conditioning, and adds pixel-aligned generation, explicit image back-projection into a 3D feature volume, and cascaded refinement of structure, shape, and texture. It generally produces better results than Trellis.2, with tighter fidelity to the input image. Both output the same PBR material set. Nothing per asset. Both models are open weights and can run locally on consumer hardware as part of ComfyUI core, so there is no per-generation charge. They are also available on Comfy Cloud, where standard Comfy Cloud credit usage applies. No. The original Trellis.2 pipeline required PyTorch 2.6.0 with CUDA 12.4 and a stack of compiled extensions. The native ComfyUI implementation drops all of them. If your ComfyUI runs, these models run on your current PyTorch. A single image. Both models generate geometry and materials from one input view. The workflows also include BiRefNet for background removal and MoGe for camera field-of-view estimation, both available on the Comfy-Org Hugging Face page. Comfy-Org/TRELLIS.2 and Comfy-Org/Pixal3D from Hugging Face, plus Comfy-Org/BiRefNet for background removal and Comfy-Org/MoGe for camera FOV estimation. The workflow note lists the target directory for each. Trellis.2's texturing model produces base color, roughness, and metallic maps. The ComfyUI implementation adds a UV unwrapping node and bakes two more maps from the high-poly mesh: a normal map and an ambient occlusion map, giving a complete PBR material set. Four new nodes ship with this release. Remesh Mesh fixes holes and mesh imperfections, Decimate Mesh reduces face and vertex count to a target budget, Smooth Mesh Normals smooths the mesh volume, and Render Mesh produces a quick image render. The Load 3D, Preview 3D, and Save 3D nodes were also rebuilt for these workflows. Open this workflow in Comfy Cloud This run: 6 credits — free for you ### 5 free runs. No card. Your image is saved. The run starts the moment you’re in. By continuing you agree to the Terms. Open source stays open — your graphs and outputs are yours.