FLUX
Black Forest Labs FLUX is a repository that offers minimal inference code to run image production and editing with its open weight models. It supports model variants for production from text to image, internal/external dyeing, Canny and depth and structural conditioning, image variation and image editing. The model licenses are different: FLUX.1 [schnell] is Apache-2.0, while [giant] variants are distributed under the FLUX.1-giant Non-Commercial License.
FLUX
55black-forest-labs · Local AI / Self-Hosted LLM
Common commercial products in this category: ChatGPT, Claude, Gemini
- You can generate images from text by installing the FLUX.1 [schnell] model in its local environment.
- You can run the model using the NVIDIA infrastructure with TensorRT support
- You can perform in/out-painting (internal and external dyeing) with FLUX.1 Fill [giant]
- • Last update over 1 year ago
- ↑ PositiveHacker News
FLUX 3 Image
“What are the best benchmarks to compare these kind (image, video etc.) of generative models - difficult to compare? That would be to compare e.g. Qwen Image 3.0 with FLUX 3, with Midjourney etc. I had seen some attempts - but I do not know well how they try to approach…”
- • NeutralGitHub Issue
Fine-tuning code
“Congrats on the release! Will code be released to fine-tune the [schnell] model? (is it even fine-tuneable?)”
Verified against README · Oct 26, 2026 · source