lovis93

`FLUX.1 [dev]` is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. For more information, please read our blog post. Key Features 1. Cutting-edge output quality, second only to our state-of-the-art model `FLUX.1 [pro]`. 2. Competitive prompt following, matching the performance of closed source alternatives . 3. Trained using guidance distillation, making `FLUX.1 [dev]` more efficient. 4. Open weights to drive new scientific research, and empower artists to develop innovative workflows. 5. Generated outputs can be used for personal, scientific, and commercial purposes as described in the [`FLUX.1 [dev]` Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md). Usage We provide a reference implementation of `FLUX.1 [dev]`, as well as sampling code, in a dedicated github repository. Developers and creatives looking to build on top of `FLUX.1 [dev]` are encouraged to use this as a starting point. API Endpoints The FLUX.1 models are also available via API from the following sources - bfl.ml (currently `FLUX.1 [pro]`) - replicate.com - fal.ai - mystic.ai ComfyUI `FLUX.1 [dev]` is also available in Comfy UI for local inference with a node-based workflow. To use `FLUX.1 [dev]` with the 🧨 diffusers python library, first install or upgrade diffusers To learn more check out the diffusers documentation --- Limitations - This model is not intended or able to provide factual information. - As a statistical model this checkpoint might amplify existing societal biases. - The model may fail to generate output that matches the prompts. - Prompt following is heavily influenced by the prompting-style. Out-of-Scope Use The model and its derivatives may not be used - In any way that violates any applicable national, federal, state, local or international law or regulation. - For the purpose of exploiting, harming or attempting to exploit or harm minors in any way; including but not limited to the solicitation, creation, acquisition, or dissemination of child exploitative content. - To generate or disseminate verifiably false information and/or content with the purpose of harming others. - To generate or disseminate personal identifiable information that can be used to harm an individual. - To harass, abuse, threaten, stalk, or bully individuals or groups of individuals. - To create non-consensual nudity or illegal pornographic content. - For fully automated decision making that adversely impacts an individual's legal rights or otherwise creates or modifies a binding, enforceable obligation. - Generating or facilitating large-scale disinformation campaigns. License This model falls under the [`FLUX.1 [dev]` Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).

🎉 ✨ UPDATE - Version 2 Now Available! (21 Oct 2025) ✨ 🎉 What's New in V2: - 🎯 Trained on higher quality data for significantly improved results - 💪 Better command responsiveness - the model fol...

Push-in camera — A Motion LoRA for Wan 2.1 (14B - 720p) This LoRA was trained on 100 clips to introduce realistic, high-quality push-in drone camera motion into your generations. While the Wan 2.1 I2V 720p model produces great image quality, it can sometimes lack meaningful movement. `Push-in camera` enhances your creations by delivering natural camera dynamics across various styles and scenes. This final version is the result of over 40 iterations of tweaking and refining to achieve a truly cinematic motion. To use this LoRA, you need to use the trigger word `Push-in camera` in your prompt. Example prompt: `Push-in camera, Instantly rocketing towards the heart of the lavender field, the vibrant purple blooms blurring into a hypnotic, swirling vortex of color as the rows of lavender, each individual flower a tiny point of light, rush towards the viewer, the distant cypress trees transforming into sharp, dark silhouettes against a breathtaking sunset sky, the soft golden light illuminating every minute detail of the scene, until the camera slams into the heart of the field, revealing the intricate texture of the blossoms, the delicate variations in purple hues, and the subtle golden undertones of the setting sun, in breathtaking, hyper-real clarity.` A complete ComfyUI workflow is available to help you get started instantly. This makes the LoRA directly usable without any complex setup. You can download the workflow file here: workflow-pushin-v2-comfyui.json Here are some examples of the push-in effect generated with this LoRA. | Input Image | Generated Video | | :---: | :---: | | | | | | | - Base Model: Wan 2.1 I2V 720p - Trigger Word: `Push-in camera` - Training: Trained on 100 carefully curated clips. - Compatibility: Ideal for cinematic sequences, storytelling shots, and dynamic framing. It adapts beautifully across all styles. This LoRA is also available on Civitai. I'm curious to hear your feedback! Feel free to open an issue or reach out with any questions.