ai-models/FLUX.1-Kontext-dev
2
0
Fork 0
mirror of https://www.modelscope.cn/black-forest-labs/FLUX.1-Kontext-dev.git synced 2026-04-02 18:12:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
ai-modelscope
2025-06-29 03:45:27 +08:00
parent d9384169a3
commit 198429de8a
1 changed files with 0 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@ -95,7 +95,6 @@ For VRAM saving measures and speed ups check out the [diffusers docs](https://hu
# Risks # Risks
Risks
Black Forest Labs is committed to the responsible development of generative AI technology. Prior to releasing FLUX.1 Kontext, we evaluated and mitigated a number of risks in our models and services, including the generation of unlawful content. We implemented a series of pre-release mitigations to help prevent misuse by third parties, with additional post-release mitigations to help address residual risks: Black Forest Labs is committed to the responsible development of generative AI technology. Prior to releasing FLUX.1 Kontext, we evaluated and mitigated a number of risks in our models and services, including the generation of unlawful content. We implemented a series of pre-release mitigations to help prevent misuse by third parties, with additional post-release mitigations to help address residual risks:
1. **Pre-training mitigation**. We filtered pre-training data for multiple categories of “not safe for work” (NSFW) content to help prevent a user generating unlawful content in response to text prompts or uploaded images. 1. **Pre-training mitigation**. We filtered pre-training data for multiple categories of “not safe for work” (NSFW) content to help prevent a user generating unlawful content in response to text prompts or uploaded images.
2. **Post-training mitigation.** We have partnered with the Internet Watch Foundation, an independent nonprofit organization dedicated to preventing online abuse, to filter known child sexual abuse material (CSAM) from post-training data. Subsequently, we undertook multiple rounds of targeted fine-tuning to provide additional mitigation against potential abuse. By inhibiting certain behaviors and concepts in the trained model, these techniques can help to prevent a user generating synthetic CSAM or nonconsensual intimate imagery (NCII) from a text prompt, or transforming an uploaded image into synthetic CSAM or NCII. 2. **Post-training mitigation.** We have partnered with the Internet Watch Foundation, an independent nonprofit organization dedicated to preventing online abuse, to filter known child sexual abuse material (CSAM) from post-training data. Subsequently, we undertook multiple rounds of targeted fine-tuning to provide additional mitigation against potential abuse. By inhibiting certain behaviors and concepts in the trained model, these techniques can help to prevent a user generating synthetic CSAM or nonconsensual intimate imagery (NCII) from a text prompt, or transforming an uploaded image into synthetic CSAM or NCII.