GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
black-forest-labs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
black-forest-labs
Model Tree
Qwen/Qwen3.5-9B
Input Modalities
Output Modalities
Supported Functionality
sh
hf download black-forest-labs/flux-3-image-klein-pup --local-dir weights/puppython scripts/cli.py "A man walking with his dog, afternoon sun" --out out.pngThe upsampler is on by default; --no-pup sends the prompt as typed. To upsample without generating: python -m flux3.pup --prompt "..." --out caption.txt. Install, references and the box format: black-forest-labs/flux-3-image-klein.
python
import json import torchfrom huggingface_hub import hf_hub_downloadfrom transformers import AutoProcessor, Qwen3_5ForConditionalGeneration model_id = "black-forest-labs/flux-3-image-klein-pup"processor = AutoProcessor.from_pretrained(model_id)model = Qwen3_5ForConditionalGeneration.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto").eval()prompts = json.load(open(hf_hub_download(model_id, "system_prompts.json"))) messages = [{"role": "system", "content": prompts["t2i"]}, {"role": "user", "content": "A man walking with his dog, afternoon sun"}]inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", enable_thinking=False).to(model.device)with torch.no_grad(): out = model.generate(**inputs, max_new_tokens=3584, do_sample=False)caption = processor.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True).strip()print(caption)For an edit, use prompts["i2i"] and a user message with the reference images first ({"type": "image", "image": pil_image} per reference) and then this text, three lines:
text
Reference images follow in order (the first image, the second image, ...).User request: put a red bandana around the dog's neckOutput the caption.Decoding: greedy, top_p 0.95, top_k 20, presence penalty 1.5 for text-to-image and 0 for edits. The *_bbox prompts take the boxes as JSON after the request and return the prompt with a box table; the exact scaffolds are flux3/pup.py and flux3/bbox.py in the inference code.
--safety).This model is released under the Apache License 2.0. It is derived from Qwen3.5-9B by the Qwen team at Alibaba Cloud, released under the Apache License 2.0.
This project may contain trademarks or logos for projects, products, or services. Use of Black Forest Labs and FLUX trademarks or logos in modified versions of this project must not cause confusion or imply sponsorship or endorsement. Any use of third-party trademarks, intellectual property or logos are subject to those third-party's policies.
If you use FLUX 3 Image in your work, please cite:
bibtex
@misc{bfl2026flux3image, author = {{Black Forest Labs}}, title = {{FLUX} 3 Image Klein}, year = {2026}, url = {https://bfl.ai/blog/flux-3-image-klein},}hf download black-forest-labs/flux-3-image-klein-pup --local-dir weights/puppython scripts/cli.py "A man walking with his dog, afternoon sun" --out out.pngimport json import torchfrom huggingface_hub import hf_hub_downloadfrom transformers import AutoProcessor, Qwen3_5ForConditionalGeneration model_id = "black-forest-labs/flux-3-image-klein-pup"processor = AutoProcessor.from_pretrained(model_id)model = Qwen3_5ForConditionalGeneration.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto").eval()prompts = json.load(open(hf_hub_download(model_id, "system_prompts.json"))) messages = [{"role": "system", "content": prompts["t2i"]}, {"role": "user", "content": "A man walking with his dog, afternoon sun"}]inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", enable_thinking=False).to(model.device)with torch.no_grad(): out = model.generate(**inputs, max_new_tokens=3584, do_sample=False)caption = processor.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True).strip()print(caption)Reference images follow in order (the first image, the second image, ...).User request: put a red bandana around the dog's neckOutput the caption.@misc{bfl2026flux3image, author = {{Black Forest Labs}}, title = {{FLUX} 3 Image Klein}, year = {2026}, url = {https://bfl.ai/blog/flux-3-image-klein},}