This is an FP8 / INT8 quantized version of FLUX 3 Image Klein (the 16-step distilled checkpoint). - Optimized for efficient inference with reduced memory footprint: the transformer is 6.44 GB instead of 11.1 GB. Same-seed LPIPS vs the bf16 model (lower is better): 0.035 INT8, 0.036 FP8. - Loads pre-quantized in Unsloth Desktop, which skips the bf16 download and the on-the-fly quantization. The text encoder (Qwen3-VL-4B-Instruct) and the VAE are unchanged; take them from black-forest-labs/flux-3-image-klein. The text encoder rows are scored against the bf16 text encoder with the bf16 transformer, so they measure only the encoder. The VAE stays bf16. This repo also carries the upstream diffusers folders from black-forest-labs/flux-3-image-klein, unchanged (`modular_model_index.json`, `text_encoder/`, `transformer/`, `vae/`), so Unsloth Desktop downloads every component from here.
This is a GGUF quantized version of FLUX 3 Image Klein by Black Forest Labs, the 5.6B image transformer (16-step distilled checkpoint) for text to image and image editing. unsloth/flux-3-image-klein-GGUF uses Unsloth Dynamic 2.0 methodology: the `UD-` files are mixed precision, with every layer's type chosen from a measured sensitivity scan, and they beat the uniform files at the same size. - Loads in diffusers through `Flux3Transformer2DModel.from_single_file(..., quantization_config=GGUFQuantizationConfig(...))`. Also loads in Unsloth Desktop. - Tensor names follow the original Black Forest Labs checkpoint layout. The text encoder (Qwen3-VL-4B-Instruct) and the VAE are unchanged; take them from black-forest-labs/flux-3-image-klein. **Recommended:** `UD-Q4_K_XL` (3.93 GB) for most GPUs: LPIPS 0.038 against 0.060 for `Q4_K_M`. For output closest to bf16 use `Q8_0`; on small cards use `UD-Q2_K_XL` (2.62 GB). LPIPS (alex, lower is better) and SSIM against the bf16 transformer, same prompt, seed, noise and text encoder, 16 steps, over 19 renders: 8 held-out prompts at 1024x1024 plus 11 text-to-image and editing cases (single and multi-reference). A repeated bf16 render scores 0, so the numbers measure only the quantization.
**V4 Candidates** LoRA A: qwen-edit-enhance-v4-16_a_000003000/1000, LoRA B: qwen-edit-enhance-v4-64_a_000003750/4750 Prompt: Enhance image quality, followed by textual description of the scene. The more descriptive it is, the better the upscale effect will be All images below are from 8 step Lighting LoRA. * ModelSamplingAuraFlow is a must, shift must be kept **below** 0.3. With higher resolutions, such as image 3, you can set it as low as 0.02 * Samplers - LCM (best), Euler_Ancestral, then Euler * Schedulers all work and give varying results in terms of smoothness
We introduce FireRed-Image-Edit-1.1, an upgrade to our general-purpose image editing foundation model. Building upon the capabilities presented in the FireRed-Image-Edit-1.0 Technical Report, version 1.1 significantly enhances identity consistency, multi-image conditioning, and domain-specialized editing performance, bringing the model closer to real-world creative production needs.
We introduce **LongCat-Image-Edit**, the image editing version of Longcat-Image. LongCat-Image-Edit supports bilingual (Chinese-English) editing, achieves state-of-the-art performance among open-source image editing models, delivering leading instruction-following and image quality with superior visual consistency.
We introduce **LongCat-Image-Edit-Turbo**, the distilled version of LongCat-Image-Edit. It achieves high-quality image editing with only 8 NFEs (Number of Function Evaluations) , offering extremely low inference latency.
> 🚀 **Try Online / 在线一键体验** > > Don't have a high-end GPU? You can run and test this model directly on RunningHub without local setup: > > 无需本地部署显卡,点击下方链接即可在 RunningHub 上直接运行与体验该工作流: > 👉 **Click Here to Run on RunningHub / 在线运行链接** > *Special thanks to our community group members for their valuable test feedback! Unless critical issues arise, V3 will serve as the final release for the foreseeable future. For commercial inquiries, feel free to reach out.* 🙏 > ⚡ **Compute Sponsor / 算力支持致谢** > > Special thanks to our compute sponsor for providing the GPU acceleration required to train and fine-tune this 2048px model! > > 本模型的 2048 高清微调训练离不开算力赞助方的大力支持,非常感谢!欢迎扫码关注/支持算力提供方: > > > > > >