Search public pages, research tools, and SAVRN solutions.
Open-weight model · Image to image
by Black Forest Labs black-forest-labs/FLUX.2-small-decoder
FLUX.2-small-decoder is an open-weight model for image to image from Black Forest Labs, released under Apache License 2.0. It has 62M parameters. At 16-bit it needs about 0.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 218.2k downloads a month.
FLUX.2 Small Decoder is a distilled VAE decoder that serves as a drop-in replacement for the standard FLUX.2 decoder. It delivers faster decoding and lower VRAM usage with minimal to zero quality loss. The encoder remains unchanged. 1.
What it takes to serve FLUX.2-small-decoder (62M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 10, 2026.
FLUX.2-small-decoder on every accelerator the SAVRN Index prices, at every precision
By Black Forest Labs, published under apache-2.0, revision a3efc24f613e.
FLUX.2 Small Decoder is a distilled VAE decoder that serves as a drop-in replacement for the standard FLUX.2 decoder. It delivers faster decoding and lower VRAM usage with minimal to zero quality loss. The encoder remains unchanged.
[96, 192, 384, 384] vs [128, 256, 512, 512]).Compatible with all open FLUX.2 models: - FLUX.2-klein-4B - FLUX.2-klein-9B - FLUX.2-klein-9b-kv - FLUX.2-dev
| Full Decoder | Small Decoder |
|---|---|
pip install git+https://github.com/huggingface/diffusers.git
10 files, 619.4 MB in total. The weights are 3 files totalling 610.8 MB in safetensors.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| diffusion_pytorch_model.safetensors | Weights | 249.5 MB | d8d52ba03647 |
| full_encoder_small_decoder.safetensors | Weights | 249.5 MB | ea4273f02d1f |
| small_decoder.safetensors | Weights | 111.8 MB | ad7833477475 |
| config.json | Configuration | 842 B | — |
| README.md | Documentation | 3.9 KB | — |
| compare_full_decoder.png | Other | 1.2 MB | 188624cc1d06 |
| compare_small_decoder.png | Other | 1.3 MB | 3ceccc1bea55 |
| comparison_panel.jpeg | Other | 3.5 MB | ea01b25d80d3 |
| editing.jpg | Other | 2.5 MB | 2912ca5a7cb9 |
| .gitattributes | Repository | 1.7 KB | — |
Released by Black Forest Labs through its official repository on Hugging Face. Read the license.
| Precision | Weights in memory |
|---|---|
| As published | 610.8 MB |
| 16-bit | 0.1 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (62M parameters) plus a working margin. A long context needs more.
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Yes. FLUX.2-small-decoder is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
This model is a custom PyTorch U-Net architecture (SketchUNet) trained to convert RGB photos into target outline sketches using the rhfeiyang/photo-sketch-pair-500 dataset. - Combined Sketch Loss (L1 + Sobel Edge Loss): 0.14555 - Mean Absolute Error (L1 / MAE): 0.04962 This model converts an RGB image into a grayscale sketch using a PyTorch U-Net architecture. The model checkpoint is available as: Once the model architecture is defined, inference can be reduced to
Status: evaluated app-testing candidate. Some broad color patches and incorrect object hues remain. Predicted colors are not evidence of original historical colors. This checkpoint has 3,968,892 learned parameters and 236 fixed color bins. It starts from the audited bin-mapping repair of main commit 6c47ea40724d8fcd67d4f36ce837dc1cb5b1b2a8 and changes all 65 learned parameter tensors. The color vocabulary is unchanged. The selected weights are update 748 of a completed 1,122-update BF16 L4 run using a 17,325-photo mixed training pool (11,943 Imagenette plus 5,382 COCO), batch 32, initial learning rate 1e-5, weighted classification loss and frozen BatchNorm running statistics. Selection…
Try MadStickArt online → — generate a storyboard in your browser before downloading. Adjust composition and camera controls, then export clean or annotated PNGs and scene JSON. The playground runs the released neural decoder locally and uses optional rule-based scene suggestions; Strands Decider is available in the downloadable Python pipeline. MadStickArt is a small, trained 12,192-parameter image model for clean stick-figure storyboard scenes at 956 × 400 pixels, exactly 2.39:1. This first public release is danger-room/MadStickArt-v0.1.0, licensed under Apache 2.0. Pin revision v0.1.0 for reproducible downloads. The model is a custom PyTorch layout-conditioned neural raster decoder. A…
This is a GGUF quantized version of FLUX.2-klein-4B. unsloth/FLUX.2-klein-4B-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. - Important layers are upcasted to higher precision. - Uses tooling from ComfyUI-GGUF by city96. The FLUX.2 [klein] model family are our fastest image models to date. FLUX.2 [klein] unifies generation and editing in a single compact architecture, delivering state-of-the-art quality with end-to-end inference in as low as under a second. Built for applications that require real-time image generation without sacrificing quality, and runs on consumer hardware, with as little as 13GB VRAM. FLUX.2 [klein] 4B is a 4 billion parameter rectified flow…
FLUX.2 [klein] 4B is a 4 billion parameter rectified flow transformer capable of generating images from text descriptions and supports multi-reference editing capabilities. For more information, please read our blog post. This repository holds an FP8 version of FLUX.2 [klein] 4B. The main repository of this model (full BF16 weights) can be found here. Limitations - This model is not intended or able to provide factual information. - While the model can output text, text rendered may be inaccurate or subject to distortion. - As a statistical model, this checkpoint may represent or amplify biases observed in the training data. - The model may fail to generate output that matches the prompts.…
A LoRA adapter for the Qwen-Image-Edit-2511 diffusion pipeline, enabling NSFW content generation and editing capabilities. The easiest way to use this LoRA is through the ScottzillaSystems Image Editor — select " MCNL-NSFW-v1" from the adapter dropdown. Use these concepts in your prompts to activate specific capabilities: nsfw nipples vagina penis missionary cowgirlout reversecowgirlpov blowjob cumonface creamp1e l1ck