TRELLIS.2-4B is a 3D generation model that none of the candidate sources names directly; the closest matches are hosting platforms that run open models through an API. Hugging Face hosts open models and offers an SDK and skills for them 3, and Replicate runs open-source models through a cloud API, including a Rodin model that generates 3D models from images 5.
- 1
Hugging Facehuggingface.coverified and signed
Hosts open-source models, datasets and applications across modalities including 3D, with an official huggingface-hub SDK for working with them 3.
official:MCP server · @huggingface/mcp-clientSDK · huggingface-hubCLI · text-embeddings-inferencerepository · pwc-cliskill · hf-cli+23 community tools built for it
for agents: create_image · huggingface-vision-trainer · document_question_answering
- 2
Replicatereplicate.comverified and signed
Runs open-source machine learning models through a cloud API, including hyper3d/rodin, which generates complex 3D models from images 5.
+14 community tools built for it
for agents: bytedance/seedream-3 · hyper3d/rodin · black-forest-labs/flux-2-klein-4b
- 3
Sources
- 3Hugging Face – The AI community building the future.huggingface.co · read 2026-10-29
- 5Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 8LocalAI · Make AI run on every machinelocalai.io · read 2026-10-29
For agents: the 10 actions behind this answer
nano-banana-pro-openrouter · nano-banana-pro-openrouter verified and signed
Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. Use for prompt-only image generation, image edits, and multi-image compositing; supports 1K/2K/4K output.
generate_image · OpenAI (Activepieces) verified and signed
Generate Image — Create an image from a text description.
create_image · Hugging Face (Activepieces) verified and signed
Create Image — Generate stunning images from text prompts using state-of-the-art diffusion models - perfect for marketing, product design, and creative content
generate_images · project-montage found in code, not yet checked
Generates images on the provided visual description or Edits reference images by adding characters or modifying it based on a visual description using the Nano Banana model. Supports parallel generation of multiple requests. This tool can be used to generate first-frame images for video generation.
bytedance/seedream-3 · bytedance/seedream-3 verified and signed
A text-to-image model with support for native high-resolution (2K) image generation
CreateCustomModel · Amazon Bedrock verified and signed
Creates a new custom model in Amazon Bedrock.
muapi_image_generate · Muapi verified and signed
Generate an image from a text prompt using muapi.ai. Returns a request_id to poll with muapi_predict_result.
text_to_speech · LocalAI (Activepieces) verified and signed
Text to Speech — Turn text into a spoken audio file.
image+text+file->text · OpenAI: GPT-5.2 Pro (batch) verified and signed
Takes image, text, file; returns text.
· Modellix website read, tools not yet checked
One unified API for AI media generation. World-class image, video, audio & text. Transparent pricing, full call logs, enterprise-grade uptime.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.