Speridlabs Iris-Z
Speridlabs Iris-Z is FLUX.2 fine-tuned to denoise an image and its depth in one sequence. The same weights generate images from a prompt, estimate depth from a photo in 4 steps, paint a prompt onto a given depth, and return an image together with its depth. LibreYOLO runs it through the LibreGen factory in two sizes.
- Tác vụ
- image generation, depth
- Kích thước
- 9b, 32b at 1024 px
- Cài đặt
pip install "libreyolo[gen]"- Bậc hỗ trợ
- Bậc song hành, từ v1.8.0. Một bề mặt sản phẩm riêng với factory và contract riêng.
- Giấy phép
- Mã nguồn MIT and Apache-2.0, trọng số FLUX Non-Commercial License. Sử dụng thương mại
Install
pip install "libreyolo[gen]"Predict
The task is fixed when the model loads: task="depth" for image to depth,
the default generate for the other three modes. A depth model never loads a
text encoder.
from libreyolo import LibreGen, SAMPLE_IMAGE model = LibreGen("speridlabs-iris-z", task="depth") # 9b; loads no text encoderresult = model(SAMPLE_IMAGE) depth = result.depth_mapprint(depth.encoding) # "log_depth": larger is fartherprint(depth.data.shape) # (H, W) at the photo's sizeprint(depth.valid_mask.shape) # False on skyresult.save("depth.png") # coloured depthfrom libreyolo import LibreGen model = LibreGen("speridlabs-iris-z")result = model("a lighthouse at dusk", seed=0)result.generated.save("lighthouse.png")from libreyolo import LibreGen, SAMPLE_IMAGE model = LibreGen("speridlabs-iris-z")# The photo's depth is estimated first, then a new scene is painted on it.result = model("a sunken ruin under the sea", source=SAMPLE_IMAGE, seed=0)result.generated.save("ruin.png")from libreyolo import LibreGen model = LibreGen("speridlabs-iris-z")result = model("a grand old library, a spiral staircase", depth=True, seed=0)result.generated.save("library.png")print(result.depth_map.data.shape)libreyolo generate prompt="a lighthouse at dusk" model=speridlabs-iris-zlibreyolo generate source=https://raw.githubusercontent.com/LibreYOLO/libreyolo/release/libreyolo/assets/guggenheim-bilbao.jpg task=depthlibreyolo generate source=photos/ task=depth ensemble=10 imgsz=1024Image to depth. Sources are what predict takes. result.depth_map is a
DepthMap with encoding="log_depth" (relative log depth, larger is
farther) at the source's size, and valid_mask is False on sky. imgsz is
the working resolution, 512 or 1024 (default 512 under half a megapixel, else
1024). Knobs: steps (4) and ensemble (1), the per-pixel median over that
many seeds. The default seed is 0, so depth repeats. save=True writes the
coloured map under runs/depth/predict.
Text to image. Prompts, imgsz, seed and n work as for every
image generation model. Knobs: steps (50)
and guidance (4.0 for 9b, 3.5 for 32b).
Depth to image. source= on the generate task is the depth the image is
painted on: a photo (its depth is estimated first), a Results or DepthMap
from any depth model, or a grayscale depth image with depth_format="depth"
(bright is far) or "disparity" (bright is near). An image is only read as a
depth map when depth_format says so. The output keeps the depth's aspect
ratio, and Results.depth_map is the depth it was painted on.
Image plus depth. depth=True samples image and depth jointly, then
re-estimates the depth from the finished image, as upstream does by default.
The result carries both result.generated and result.depth_map.
The CLI covers text to image and image to depth; prompt= and source= stay
mutually exclusive there.
Variants
| Size | Alias | Parameters | Text encoder | GPU memory (library figure) |
|---|---|---|---|---|
9b | speridlabs-iris-z, -9b, -small | 9.1B, from FLUX.2 [klein] Base 9B | Qwen3 8B FP8 | about 18 GB, plus 9 GB text encoder and 0.2 GB VAE |
32b | speridlabs-iris-z-32b, -big | 32.2B, from FLUX.2 [dev] | Mistral Small 3.2 24B | about 64 GB, plus 48 GB text encoder and 0.2 GB VAE |
offload=True keeps the text encoder on the CPU between prompts. On CUDA
without the FP8 kernel that transformers asks for (the kernels package),
and on MPS or CPU, the 9b text encoder runs dequantized in bfloat16, close
to but not identical with upstream's embeddings. A local snapshot or variant
folder loads with LibreGen(path).
Export
| Tác vụ | ONNX | TorchScript | ExecuTorch | TensorRT | OpenVINO | Paddle | MNN | RKNN | Axelera | ncnn | TFLite | CoreML | Core AI |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Image generation | Image generation to ONNX: không được hỗ trợ | Image generation to TorchScript: không được hỗ trợ | Image generation to ExecuTorch: không được hỗ trợ | Image generation to TensorRT: không được hỗ trợ | Image generation to OpenVINO: không được hỗ trợ | Image generation to Paddle: không được hỗ trợ | Image generation to MNN: không được hỗ trợ | Image generation to RKNN: không được hỗ trợ | Image generation to Axelera: không được hỗ trợ | Image generation to ncnn: không được hỗ trợ | Image generation to TFLite: không được hỗ trợ | Image generation to CoreML: không được hỗ trợ | Image generation to Core AI: không được hỗ trợ |
| Depth | Depth to ONNX: không được hỗ trợ | Depth to TorchScript: không được hỗ trợ | Depth to ExecuTorch: không được hỗ trợ | Depth to TensorRT: không được hỗ trợ | Depth to OpenVINO: không được hỗ trợ | Depth to Paddle: không được hỗ trợ | Depth to MNN: không được hỗ trợ | Depth to RKNN: không được hỗ trợ | Depth to Axelera: không được hỗ trợ | Depth to ncnn: không được hỗ trợ | Depth to TFLite: không được hỗ trợ | Depth to CoreML: không được hỗ trợ | Depth to Core AI: không được hỗ trợ |
export(), train() and val() raise, as for every LibreGen family.
Licensing
Hãy kiểm tra giấy phép trong repo Hugging Face của trọng số cụ thể mà bạn tải xuống. Mỗi checkpoint trong tổ chức LibreYOLO đều có giấy phép riêng và giấy phép có thể khác nhau trong cùng một họ. Repo đó là nguồn có thẩm quyền; phần tóm tắt dưới đây mô tả các điều khoản áp dụng khi trang này được kiểm chứng lần gần nhất.
Đây là phần mô tả các giấy phép liên quan, không phải tư vấn pháp lý. Nếu câu trả lời có ý nghĩa về mặt thương mại, hãy tự đọc các giấy phép và tham khảo cố vấn của riêng bạn.
- Công trình gốc
- Speridlabs Iris-Z, Speridlabs
- Giấy phép thượng nguồn
- FLUX Non-Commercial License
- Nguồn thượng nguồn
- github.com/speridlabs/iris-z-sdk
- Mã nguồn LibreYOLO
- MIT
- Trọng số
- FLUX Non-Commercial License, do tác giả phân phối. LibreYOLO không lưu trữ hoặc sao chép chúng.
- Diễn giải
- The Iris-Z weights are derived from FLUX.2 [dev] and FLUX.2 [klein] Base 9B and are under Black Forest Labs' FLUX Non-Commercial License, a custom agreement that is not OSI-approved: no commercial or production use, and Section 2(e) asks for content filtering or human review of generated images before they are shared. LibreYOLO's adapter is MIT; the transformer, samplers and prompt embedders it ports from the Speridlabs Iris-Z SDK keep Apache-2.0, as does the FLUX.2 code the SDK builds on, with their notices in libreyolo/models/gen/speridlabs_irisz/NOTICE. LibreYOLO does not redistribute any weights. They download at runtime, unmodified, from their publishers at pinned revisions: speridlabs/iris-z at 16239e1a5444c484b11a04b61d633eceb768574c (9b from Iris-Z-small, 32b from Iris-Z-big, not gated), the FLUX.2 VAE from black-forest-labs/FLUX.2-klein-4B (Apache-2.0), and the text encoders Qwen/Qwen3-8B-FP8 for 9b and mistralai/Mistral-Small-3.2-24B-Instruct-2506 for 32b (both Apache-2.0).
Speridlabs Iris-Z is by Speridlabs. The weights are under Black Forest Labs' FLUX Non-Commercial License: no commercial or production use, and section 2(e) asks for content filtering or human review of generated images before they are shared. LibreYOLO's adapter is MIT; the transformer, samplers and prompt embedders ported from the Iris-Z SDK keep Apache-2.0.
LibreYOLO does not redistribute any weights. They download at runtime,
unmodified, from speridlabs/iris-z at a pinned revision, not gated. The
FLUX.2 VAE comes from the Apache-2.0 black-forest-labs/FLUX.2-klein-4B
repository, and the text encoders (Qwen/Qwen3-8B-FP8 for 9b,
mistralai/Mistral-Small-3.2-24B-Instruct-2506 for 32b) are Apache-2.0.
Citation
@article{canada2026irisz,
title = {Iris-Z: Scaling One Generative Model Past
Specialist Geometry Models},
author = {Ca{\~n}ada, Alejandro and Garabito, Chema},
journal = {arXiv preprint arXiv:2611.16010},
year = {2026},
url = {https://arxiv.org/abs/2611.16010}
}Được sao chép từ khối trích dẫn của tác giả tại speridlabs.com/research/iris-z#citation.