Instructions to use savagemanage/redrob-image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use savagemanage/redrob-image with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("savagemanage/redrob-image", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
| Redrob Image | |
| ============ | |
| Copyright 2026 Redrob (https://redrob.io) | |
| Copyright 2026 Janghoon Lee (https://www.janghoonlee.com) | |
| Date: August 5, 2026 | |
| Licensed under the Apache License, Version 2.0. | |
| https://www.apache.org/licenses/LICENSE-2.0 | |
| This distribution is a modified derivative of Z-Image-Turbo. | |
| --------------------------------------------------------------------------- | |
| Upstream attribution | |
| --------------------------------------------------------------------------- | |
| This product includes model weights derived from: | |
| Tongyi-MAI / Z-Image-Turbo | |
| https://huggingface.co/Tongyi-MAI/Z-Image-Turbo | |
| https://github.com/Tongyi-MAI/Z-Image | |
| Licensed under the Apache License, Version 2.0. | |
| Copyright notices from the upstream project are retained to the extent | |
| applicable. | |
| --------------------------------------------------------------------------- | |
| Modifications by Redrob (built by Janghoon Lee) | |
| --------------------------------------------------------------------------- | |
| - Style adapter baked into the UNET at strength 0.7 (ComfyUI | |
| LoraLoaderModelOnly -> state_dict bake). | |
| - Branded the distribution artifact as Redrob Image | |
| (modelspec + redrob.* safetensors metadata). | |
| - Packaged for ComfyUI UNETLoader (diffusion_models layout) and as a | |
| Diffusers ZImageTransformer2DModel under transformer/. | |
| --------------------------------------------------------------------------- | |
| Companion weights (not in this package by default) | |
| --------------------------------------------------------------------------- | |
| Runtime still typically requires (from Comfy-Org / Tongyi packs): | |
| - qwen_3_4b_fp8_mixed.safetensors (text encoder) | |
| - ae.safetensors (VAE) | |
| See README.md. | |