46:I[603186,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"PageMetadata"] 47:I[831915,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"SearchResultsImage"] 48:I[430295,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],""] 49:I[299632,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"default"] 4a:I[400402,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"EndpointCTA"] 4b:I[331699,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"ModelContent"] 51:I[946424,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"default"] 43:["$","$L46",null,{"hasPartnerEndpoint":true}] 4c:T2635,# Overview ## Description: Qwen-Image is an image-generation foundation model in the Qwen series. It achieves significant advances in **complex text rendering** (supporting alphabetic scripts such as English and logographic scripts such as Chinese) and **precise image editing** (for example, style transfer, object addition/removal, and pose manipulation). It adopts a multi-module architecture that integrates vision-language encoding and diffusion-based generation, and delivers strong performance in general image generation, text-in-image integration, and classical computer vision tasks (for example, depth estimation and novel-view synthesis). Qwen-Image was developed by the Qwen Team. This model is ready for commercial and non-commercial use. ## Third-Party Community Consideration: These models are not owned or developed by NVIDIA. These models have been developed and built to a third-party’s requirements for this application and use case; see links to: * [Qwen/Qwen-Image Model Card](https://huggingface.co/Qwen/Qwen-Image) * [Qwen/Qwen-Image-2512 Model Card](https://huggingface.co/Qwen/Qwen-Image-2512) ### License/Terms of Use GOVERNING TERMS: The trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf); and use of this model is governed by the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). **Additional Information**: [Apache 2.0 license](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md). ### Deployment Geography: Global ### Use Case: - **Content Creation**: For artists, designers, and creators generating text-rich images (e.g., posters, UI mockups, and artistic works) and performing precise image editing. - **Educational & Professional**: For educators creating visual teaching materials (for example, mathematical diagrams with text) and professionals synthesizing documents and images (e.g., technical slides and reports). - **Research**: For computer vision and generative AI researchers studying text-image alignment, diffusion-based generation, and multimodal integration. ### Release Date: * HuggingFace/Modelscope: Qwen-Image version August 4, via https://huggingface.co/Qwen/Qwen-Image and https://modelscope.cn/models/Qwen/Qwen-Image * HuggingFace/Modelscope: Qwen-Image-2512 version December 31, 2025 via https://huggingface.co/Qwen/Qwen-Image-2512 and https://modelscope.cn/models/Qwen/Qwen-Image-2512 * build.nvidia.com April 30, 2026 via [https://build.nvidia.com/qwen/qwen-image](https://build.nvidia.com/qwen/qwen-image) ## References * [Technical Report](https://arxiv.org/abs/2508.02324) ## Model Architecture: ### Architecture Type: Qwen-Image adopts a **three-core module architecture**: 1. **Multimodal Large Language Model (MLLM)**: Qwen2.5-VL (frozen) for text/image feature extraction and semantic alignment. 2. **Variational AutoEncoder (VAE)**: Single-encoder (frozen, adapted from Wan2.1-VAE) + dual-decoder (image-specific decoder fine-tuned) for image tokenization and reconstruction. 3. **Multimodal Diffusion Transformer (MMDiT)**: Backbone diffusion model with novel **Multimodal Scalable RoPE (MSRoPE)** for joint text-image positional encoding. ### Network Architecture: - **Key Components**: - MSRoPE: Balances image resolution scaling and text positional encoding by mapping text to the diagonal of image grids. - Dual-Encoding Mechanism: Combines semantic features (from Qwen2.5-VL) and reconstructive features (from VAE) for editing consistency. - Multi-Task Training: Integrates T2I (text-to-image), TI2I (text-image-to-image), and I2I (image-to-image reconstruction) tasks. ### Number of Model Parameters: | Component | Parameter Count | |------------------|-----------------| | Qwen2.5-VL (VLM) | 7B | | VAE (Enc/Dec) | 54M / 73M | | MMDiT | 20B | | **Total** | ~27.1B | ## Input: ### Input Type(s): [Text] ### Input Format(s): - Text: String (supports English and Chinese). ### Input Parameters: - Text: One-Dimensional (1D), sequence of tokens. - Context: Native support for text prompts (unlimited length in practice, optimized for paragraph-level text). ### Other Properties Related to Input: - Pre-processing: - Text: Tokenization via Qwen2.5-VL’s tokenizer; system prompts for task alignment (e.g., T2I: detail-rich description guidance). - Context Length: No strict token limit for text prompts. ## Output: ### Output Type(s): [Image] ### Output Format: Raster image formats (e.g., png, jpg, jpeg) via VAE decoding. ### Output Parameters: Two-Dimensional (2D), with configurable resolution (supports aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3). ### Other Properties Related to Output: - Resolution: Up to 1328×1328 (default) for high-fidelity generation; supports ultra-high resolution via multi-scale training. - Text Fidelity: Preserves font, layout, and language coherence for text-in-image outputs (e.g., Chinese characters, English paragraphs). Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions. ## Software Integration: **Runtime Engines:** * SGlang Diffusion **Supported Hardware Microarchitecture Compatibility**: * NVIDIA Blackwell
* NVIDIA Hopper
* NVIDIA Lovelace
**Supported Operating Systems**: * Linux * Windows Subsystem for Linux The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment. ## Model Version(s): * Qwen-Image * Qwen-Image-2512 ## Training, Testing, and Evaluation Datasets: ### Dataset Overview: - **Total Size**: Undisclosed - **Total Number of Datasets**: 3 ### Training Dataset: - **Link**: Undisclosed - **Data Modality**: [Image, Text] - **Image Training Data Size**: Undisclosed - **Text Training Data Size**: Undisclosed - **Data Collection Method by dataset**: [Hybrid: Automated, Synthetic] - **Labeling Method by dataset**: [Hybrid: Automatic/Sensors, Human] - **Properties**: - Quantity: Undisclosed. - Descriptions: Datasets used for training included images of nature (55%, e.g., landscapes, objects), Design (27%, e.g., posters, UI), People (13%, e.g., portraits), and Synthetic Data (5%, text rendering-focused). - Sensors: Undisclosed. ### Testing Dataset: - **Link**: Undisclosed - **Data Collection Method by dataset**: Undisclosed - **Labeling Method by dataset**: Undisclosed - **Properties**: Undisclosed ### Evaluation Dataset: - **Link**: Undisclosed - **Data Collection Method by dataset**: [Automated] - **Labeling Method by dataset**: [Hybrid: Automated, Human] - **Properties**: Undisclosed. ## Key Considerations: This model can generate synthetic images and may produce content that is inaccurate, offensive, or otherwise inappropriate. Users should implement robust safety guardrails — including content filtering, abuse monitoring, and access controls— to reduce the risk of harmful outputs. Users are responsible for ensuring that their use of the model complies with all applicable laws and regulations, and for regularly reviewing and updating their guardrails as risks evolve. For more information about the implementation of Cosmos pre and post guardrails to improve model safety, please see the [Cosmos-1.0 Guardrail Model](https://huggingface.co/nvidia/Cosmos-1.0-Guardrail). ## Inference: **Engine**: SGLang Diffusion **Test Hardware**: H100 ## Ethical Considerations: NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal developer team to ensure these software components meet requirements for the relevant industry and use case and address unforeseen product misuse. Please make sure you have proper rights and permissions for all input image and video content; if image or video includes people, personal health information, or intellectual property, the image or video generated will not blur or maintain proportions of image subjects included. Users are responsible for model inputs and outputs. Users are responsible for ensuring safe integration of this model, including implementing guardrails as well as other safety mechanisms, prior to deployment. Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/). # Get Help ## Getting started with the NIM Deploying and integrating the NIM is straightforward thanks to our industry standard APIs. Visit the [Visual Generative AI NIM page](https://docs.nvidia.com/nim/visual-genai/latest/overview.html) for release documentation, deployment guides and more. ## Enterprise Support Get access to knowledge base articles and support cases or [submit a ticket](https://www.nvidia.com/en-us/data-center/products/ai-enterprise-suite/support/).4d:T557,invoke_url='https://ai.api.nvidia.com/v1/genai/black-forest-labs/flux.1-dev' authorization_header="Authorization: Bearer $NVIDIA_API_KEY" accept_header='Accept: application/json' content_type_header='Content-Type: application/json' data='{ "prompt": <%- JSON.stringify(request.prompt).replaceAll('\'', '\'\\\'\'') %>, <% if (request.mode !== "base") { %>"mode": <%- JSON.stringify(request.mode) %>, "image": "<%- request.image %>",<% } else { %>"mode": <%- JSON.stringify(request.mode) %>,<% } %> "cfg_scale": <%- request.cfg_scale %>, <% switch(request.ratio) { case "16:9": %>"width": 768, "height": 1344,<% break; case "9:16": %>"width": 1344, "height": 768,<% break; case "5:4": %>"width": 896, "height": 1152,<% break; case "4:5": %>"width": 1152, "height": 896,<% break; case "3:2": %>"width": 832, "height": 1216,<% break; case "2:3": %>"width": 1216, "height": 832,<% break; case "1:1": default: %>"width": 1024, "height": 1024,<% break; } %> "seed": <%- request.seed %>, "steps": <%- request.steps %> }' response=$(curl --silent -i -w "\n%{http_code}" --request POST \ --url "$invoke_url" \ --header "$authorization_header" \ --header "$accept_header" \ --header "$content_type_header" \ --data "$data" ) http_code=$(echo "$response" | tail -n 1) echo "$response" | awk '/{/,EOF-1' 4e:T5c9,import fetch from "node-fetch"; const invokeUrl = "https://ai.api.nvidia.com/v1/genai/black-forest-labs/flux.1-dev" const headers = { "Authorization": "Bearer $NVIDIA_API_KEY", "Accept": "application/json", } const payload = { "prompt": <%- JSON.stringify(request.prompt).replaceAll('\'', '\'\\\'\'') %>, <% if (request.mode !== "base") { %>"mode": <%- JSON.stringify(request.mode) %>, "image": "<%- request.image %>",<% } else { %>"mode": <%- JSON.stringify(request.mode) %>,<% } %> "cfg_scale": <%- request.cfg_scale %>, <% switch(request.ratio) { case "16:9": %>"width": 768, "height": 1344,<% break; case "9:16": %>"width": 1344, "height": 768,<% break; case "5:4": %>"width": 896, "height": 1152,<% break; case "4:5": %>"width": 1152, "height": 896,<% break; case "3:2": %>"width": 832, "height": 1216,<% break; case "2:3": %>"width": 1216, "height": 832,<% break; case "1:1": default: %>"width": 1024, "height": 1024,<% break; } %> "seed": <%- request.seed %>, "steps": <%- request.steps %> } let response = await fetch(invokeUrl, { method: "post", body: JSON.stringify(payload), headers: { "Content-Type": "application/json", ...headers } }); if (response.status != 200) { let errBody = await (await response.blob()).text() throw "invocation failed with status " + response.status + " " + errBody } let response_body = await response.json() console.log(JSON.stringify(response_body)) 4f:T4d1,import requests invoke_url = "https://ai.api.nvidia.com/v1/genai/black-forest-labs/flux.1-dev" headers = { "Authorization": "Bearer $NVIDIA_API_KEY", "Accept": "application/json", } payload = { "prompt": <%- JSON.stringify(request.prompt).replaceAll('\'', '\'\\\'\'') %>, <% if (request.mode !== "base") { %>"mode": <%- JSON.stringify(request.mode) %>, "image": "<%- request.image %>",<% } else { %>"mode": <%- JSON.stringify(request.mode) %>,<% } %> "cfg_scale": <%- request.cfg_scale %>, <% switch(request.ratio) { case "16:9": %>"width": 768, "height": 1344,<% break; case "9:16": %>"width": 1344, "height": 768,<% break; case "5:4": %>"width": 896, "height": 1152,<% break; case "4:5": %>"width": 1152, "height": 896,<% break; case "3:2": %>"width": 832, "height": 1216,<% break; case "2:3": %>"width": 1216, "height": 832,<% break; case "1:1": default: %>"width": 1024, "height": 1024,<% break; } %> "seed": <%- request.seed %>, "steps": <%- request.steps %> } response = requests.post(invoke_url, headers=headers, json=payload) response.raise_for_status() response_body = response.json() print(response_body) 50:T773,## Step 1. Get Credentials ::generate-api-key Export your personal credentials as environment variables: ```bash export NGC_API_KEY= ``` ## Step 2. Pull and Run the NIM Login to NVIDIA NGC so that you can pull the NIM container: ```bash echo "$NGC_API_KEY" | docker login nvcr.io --username '$oauthtoken' --password-stdin ``` Pull and run the NIM with the command below. ```bash # Create the cache directory on the host machine. export LOCAL_NIM_CACHE=~/.cache/nim mkdir -p "$LOCAL_NIM_CACHE" chmod 777 $LOCAL_NIM_CACHE docker run -it --rm --name=nim-server \ --runtime=nvidia --gpus='"device=0"' \ -e NGC_API_KEY=$NGC_API_KEY \ -p 8000:8000 \ -v "$LOCAL_NIM_CACHE:/opt/nim/.cache/" \ nvcr.io/nim/qwen/qwen-image:latest ``` You can specify the desired version of Qwen-Image by adding ``-e NIM_MODEL_VERSION=``. Available variants are `qwen-image` and `qwen-image-2512`. When you run the preceding command, the container downloads the model, initializes a NIM inference pipeline, and performs a pipeline warm up. A pipeline warm up typically requires up to three minutes. The warm up is complete when the container logs show ``Pipeline warmup: start/done``. ## Step 3. Test the NIM ```bash invoke_url="http://localhost:8000/v1/infer" output_image_path="result.jpg" response=$(curl -X POST $invoke_url \ -H "Accept: application/json" \ -H "Content-Type: application/json" \ -d '{ "prompt": "A simple coffee shop interior", "seed": 0 }') response_body=$(echo "$response" | awk '/{/,EOF-1') echo $response_body | jq .artifacts[0].base64 | tr -d '"' | base64 --decode > $output_image_path ``` For more details on getting started with this NIM including configuring using parameters, visit the [Visual GenAI NIM docs](https://docs.nvidia.com/nim/visual-genai/latest/getting-started.html).44:[["$","div",".3",{"className":"relative","children":[["$","div",null,{"className":"relative flex min-h-[194px] w-full flex-col overflow-hidden p-md sm:p-ml bg-manitoulinLightBlack","children":[["$","$L47",null,{"alt":"","className":"object-cover object-center !left-1/2 z-10 !w-1/2 brightness-20 lg:brightness-75","fill":true,"priority":true,"src":"https://assets.ngc.nvidia.com/products/api-catalog/images/qwen-image.jpg","style":{"maskImage":"linear-gradient(to left, rgba(0,0,0,1), rgba(0,0,0,0))"}}],["$","div",null,{"className":"z-30 mx-auto flex w-full max-w-screen-xl min-w-0 flex-1 flex-col items-start justify-between gap-md lg:flex-row lg:gap-ml","children":["$","section",null,{"aria-describedby":"resource-description","aria-labelledby":"resource-name","className":"flex w-full min-w-0 flex-col lg:flex-1","children":["$","div",null,{"className":"flex flex-col gap-1.5 whitespace-pre-wrap","children":[["$","$L48",null,{"className":"w-fit text-ml text-n300 lowercase hover:text-n050","href":"/qwen","children":"Qwen"}],["$","div",null,{"className":"flex flex-col items-start gap-3 lg:flex-row lg:items-center","children":[["$","h1",null,{"className":"max-w-full text-lg leading-heading font-medium break-words text-primary","data-testid":"resource-name","id":"resource-name","children":"qwen-image"}],[["$","span","AVAILABLE",{"className":"nv-badge nv-badge--kind-solid h-[18px] py-0","data-testid":"nv-badge","ref":"$undefined","children":["$undefined","Downloadable"]}]],"$undefined"]}],["$","p",null,{"className":"max-w-[85ch] text-ms text-primary","id":"resource-description","children":"Qwen-Image is a text-to-image foundation model with advanced multilingual text rendering."}],["$","div",null,{"className":"flex w-full flex-col items-start gap-md lg:flex-row lg:items-end lg:justify-between","children":[["$","div",null,{"className":"flex w-full min-w-0 flex-wrap gap-sm lg:flex-1","children":["$","$L49",null,{"artifactType":"ENDPOINT","density":"standard","labels":["cloudPartnerType:endpoint:cloud_partner_type_together","nimType:endpoint:nim_type_run_anywhere","nimType:endpoint:nim_type_upgrade_available","usecase:endpoint:usecase_image_gen","usecase:endpoint:usecase_text_to_image"],"searchRoutePath":"/models"}]}],["$","div",null,{"className":"z-30 flex w-full flex-row justify-start gap-ms sm:justify-end lg:w-auto lg:shrink-0","children":["$undefined",["$","$L4a",null,{"cta":{"text":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/","nim_available_override_url":"https://catalog.ngc.nvidia.com/orgs/nim/teams/qwen/containers/qwen-image"},"isNIMAccessRestricted":"$undefined","isNIMAvailable":true}]]}]]}]]}]}]}],["$","div",null,{"className":"pointer-events-none absolute right-0 bottom-0 left-0 z-20 h-30 bg-gradient-to-t to-transparent from-manitoulinLightBlack via-manitoulinLightBlack/70"}]]}],["$","div",null,{"className":"px-4 mx-auto flex max-w-screen-xl flex-col pt-0 lg:px-0","data-body-background":"light-black","children":["$","section",null,{"className":"flex w-full flex-col justify-between rounded-4 border-manitoulinBorderColor bg-manitoulinDarkBlack sm:rounded-6 lg:rounded-8 p-ms lg:p-lg","children":["$","$L4b",null,{"artifact":{"artifactType":"ENDPOINT","name":"qwen-image","displayName":"qwen-image","publisher":"qwen","shortDescription":"Qwen-Image is a text-to-image foundation model with advanced multilingual text rendering.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/qwen-image.jpg","labels":"$44:0:props:children:0:props:children:1:props:children:props:children:props:children:3:props:children:0:props:children:props:labels","attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"},{"key":"last_month_api_invocation_count","value":"0"},{"key":"last_month_download_count","value":"0"}],"updatedDate":"2026-05-01T19:55:32.779Z","canGuestDownload":true,"createdDate":"2026-05-01T19:55:32.779Z","description":"$4c","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy"},"endpointName":"qwen-image","endpointSpec":{"openAPISpec":{"openapi":"3.1.0","info":{"contact":{"name":"NVIDIA Support","url":"https://help.nvidia.com/"},"description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim for more details.","license":{"name":"FLUX.1 [dev] Non-Commercial License","url":"https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md"},"termsOfService":"https://nvidia.com/legal/terms-of-use","title":"NVIDIA NIM API for black-forest-labs/flux.1-dev","version":"1.0.0"},"servers":[{"url":"https://ai.api.nvidia.com/v1/"}],"paths":{"/genai/black-forest-labs/flux.1-dev":{"post":{"operationId":"_infer_infer_post","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ImageRequest"}}},"required":true},"responses":{"200":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ImageResponse"}}},"description":"Successful Response"},"422":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}},"description":"Validation Error"}},"summary":" Infer","x-nvai-meta":{"examples":[{"name":"Example 1 base","input":{"text":"a simple coffee shop interior"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/base/output/1.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"base\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 2 base","input":{"text":"a coffee shop patio"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/base/output/2.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"base\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 3 base","input":{"text":"a surreal dreamscape with waterfalls cascading, and a giant glowing moon in the background. Ethereal lighting"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/base/output/3.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"base\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 4 base","input":{"text":"photographic shot of Ancient pyramid shaped temple ruins in the foreground"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/base/output/4.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"base\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 1 canny","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/canny/input/1.jpg","text":"a bottle of lemonade on a round platter with lemons, limes, sugar bowl"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/canny/output/1.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"canny\", \"image\": \"data:image/png;example_id,0\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 2 canny","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/canny/input/1.jpg","text":"a bottle of olive oil on a table with cherry tomatoes, parmesan cheese, garlic and onions"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/canny/output/2.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"canny\", \"image\": \"data:image/png;example_id,0\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 3 canny","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/canny/input/1.jpg","text":"an artistic drawing in charcoal pencil of a wine bottle with cheese and fruit, dark strokes"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/canny/output/3.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"canny\", \"image\": \"data:image/png;example_id,0\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 1 depth","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/depth/input/1.jpg","text":"A simple coffee shop interior"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/depth/output/1.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"depth\", \"image\": \"data:image/png;example_id,1\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 2 depth","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/depth/input/3.jpg","text":"A surreal dreamscape with floating islands, waterfalls cascading into the sky, and a giant glowing moon in the background. Ethereal lighting, highly detailed, 8K resolution"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/depth/output/3.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"depth\", \"image\": \"data:image/png;example_id,2\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 3 depth","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/depth/input/4.jpg","text":"The ruins of an ancient temple lie at the bottom of the ocean, exotic fish swim nearby sea life and coral are everywhere"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/depth/output/4.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"depth\", \"image\": \"data:image/png;example_id,3\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"}],"name":"Generate a new image from a text prompt","path":"infer","returns":"Returns an Image artifact that consists from a generated image (JPEG) encoded in base64, finish reason and a seed used during the generation","templates":[{"requestEjs":{"curl":"$4d","node.js":"$4e","python":"$4f"},"response":"{\n \"artifacts\": [\n {\n \"base64\": \"...very long string...\",\n \"finishReason\": \"SUCCESS\",\n \"seed\": 1100106574\n }\n ]\n}\n","title":"Example"}]}}}},"components":{"schemas":{"Artifact":{"properties":{"base64":{"description":"A base64-encoded string of the generated image (JPEG)","examples":["/9j/4AAQSkZ...b+AVZ/9k="],"title":"Base64","type":"string"},"finishReason":{"allOf":[{"$ref":"#/components/schemas/FinishReason"}],"description":"The result of the generation process. `SUCCESS` indicates success. `ERROR` indicates an error. `CONTENT_FILTERED` indicates the result affected by the content filter"},"seed":{"description":"The seed used during generation","title":"Seed","type":"integer"}},"required":["base64","finishReason","seed"],"title":"Artifact","type":"object"},"FinishReason":{"enum":["SUCCESS","CONTENT_FILTERED","ERROR"],"title":"FinishReason","type":"string"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"title":"Detail","type":"array"}},"title":"HTTPValidationError","type":"object"},"ImageRequest":{"additionalProperties":false,"properties":{"prompt":{"description":"What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results.","maxLength":10000,"title":"Prompt","type":"string","examples":["a simple coffee shop interior"]},"height":{"default":1024,"description":"Height of the image to generate, in pixels. Only height=1024 is supported","enum":[768,832,896,960,1024,1088,1152,1216,1280,1344],"title":"Height","type":"integer"},"width":{"default":1024,"description":"Width of the image to generate, in pixels. Only width=1024 is supported","enum":[768,832,896,960,1024,1088,1152,1216,1280,1344],"title":"Width","type":"integer"},"cfg_scale":{"default":5,"description":"How strictly the diffusion process adheres to the prompt text (higher values keep your image closer to your prompt).","exclusiveMinimum":1,"maximum":9,"title":"Cfg Scale","type":"number"},"mode":{"enum":["depth","base","canny"],"type":["string"],"default":"base","description":"NIM inference mode. If canny or depth is selected an image input is required","title":"Mode"},"image":{"type":["string","null"],"description":"An image input with a depth map or canny edges used if the mode is depth or canny respectively. Preview API NIM supports only a predefined set of images. The image should be in form of `data:image/png;example_id,{example_id}` with example_id in a range [0,3]. ","examples":[null,"data:image/png;example_id,0","data:image/png;example_id,1","data:image/png;example_id,2","data:image/png;example_id,3"],"title":"Image"},"samples":{"default":1,"description":"Number of images to generate. Only samples=1 is supported","maximum":1,"minimum":1,"title":"Samples","type":"integer"},"seed":{"default":0,"description":"The seed which governs generation. Changing the seed with other inputs fixed results in different outputs. (Use 0 for a random seed)","exclusiveMaximum":4294967296,"minimum":0,"title":"Seed","type":"integer"},"steps":{"default":50,"description":"The number of diffusion steps applied to generate an output image.","maximum":100,"minimum":5,"title":"Steps","type":"integer"}},"required":["prompt"],"title":"ImageRequest","type":"object"},"ImageResponse":{"properties":{"artifacts":{"items":{"$ref":"#/components/schemas/Artifact"},"maxItems":1,"minItems":1,"title":"Artifacts","type":"array"}},"required":["artifacts"],"title":"ImageResponse","type":"object"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"title":"Location","type":"array"},"msg":{"title":"Message","type":"string"},"type":{"title":"Error Type","type":"string"}},"required":["loc","msg","type"],"title":"ValidationError","type":"object"}},"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}}},"security":[{"Token":[]}]},"namespace":"qc69jvmznzxy","updatedDate":"2026-07-23T16:48:21.608Z","nvcfFunctionId":"None","createdDate":"2026-05-01T19:55:33.185Z","attributes":{"apiDocsUrl":"https://docs.nvidia.com/nim/visual-genai/latest/getting-started.html","termsOfUse":"GOVERNING TERMS: The trial service is governed by the NVIDIA API Trial Service Terms of Use; and the use of this model is governed by the NVIDIA Open Model License. ADDITIONAL INFORMATION: [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md).\n","showUnavailableBanner":false,"cta":"$44:0:props:children:0:props:children:1:props:children:props:children:props:children:3:props:children:1:props:children:1:props:cta","maxRequests":25,"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$50"}],"specifications":{"parameters":20430401088}},"artifactName":"qwen-image"},"isLoginRequired":true,"playgroundElement":"$undefined","publisherName":"qwen","searchParams":{},"tabs":[{"label":"Model Card","icon":"book","kind":"default","id":"modelcard","href":"/qwen/qwen-image/modelcard","aliases":"$undefined"},{"label":"Deploy","kind":"default","id":"deploy","href":"/qwen/qwen-image/deploy","aliases":"$undefined"}]}]}]}]]}]] 45:["$","$L51",null,{"spec":"$44:0:props:children:1:props:children:props:children:props:endpointSpec"}]