Open-weight model · Image to image
JoyAI-Image-Edit-Plus-Diffusers
by Le Jin Jinstudio/JoyAI-Image-Edit-Plus-Diffusers
JoyAI-Image-Edit-Plus-Diffusers is an open-weight model for image to image from Le Jin, released under Apache License 2.0. It has 16.3B parameters. At 16-bit it needs about 39 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Parameters16.3B
Context—
Weights—
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve JoyAI-Image-Edit-Plus-Diffusers (16.3B 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 | 32.5 GB | 39.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 16.3 GB | 19.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 8.1 GB | 9.8 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 20, 2026.
JoyAI-Image-Edit-Plus-Diffusers on every accelerator the SAVRN Index prices, at every precision
Model Card
Identity and Version
- Repository
- Jinstudio/JoyAI-Image-Edit-Plus-Diffusers
- Publisher
- Le Jin
- Task
- Image to image
- Modality
- Image
- Library
- diffusers
- Parameters
- 16.3B parameters
- Languages
- Not stated by the source
- Revision
- 8dfddb2af6e600295fe346dacba8acbe4305afa2
- First published
- 2026-10-20
- Last updated
- 2026-10-20
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
Download from Le Jin
Released by Le Jin through its official repository on Hugging Face. Read the license.
Built From
- Derived from Qwen/Qwen3-VL-8B-Instruct
Memory Requirements
| Precision | Weights in memory |
|---|---|
| 16-bit | 32.5 GB |
| 8-bit | 16.3 GB |
| 4-bit | 8.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About JoyAI-Image-Edit-Plus-Diffusers
How much GPU memory does JoyAI-Image-Edit-Plus-Diffusers need?
About 39 GB at 16-bit and 9.8 GB at 4-bit: the weights (16.3B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run JoyAI-Image-Edit-Plus-Diffusers on?
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.
Can I use JoyAI-Image-Edit-Plus-Diffusers commercially?
Yes. JoyAI-Image-Edit-Plus-Diffusers 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.
Similar Models
This September, we are pleased to introduce Qwen-Image-Edit-2509, the monthly iteration of Qwen-Image-Edit. To experience the latest model, please visit Qwen Chat and select the "Image Editing" feature. Compared with Qwen-Image-Edit released in August, the main improvements of Qwen-Image-Edit-2509 include: Install the latest version of diffusers The following contains a code snippet illustrating how to use Qwen-Image-Edit-2509: The primary update in Qwen-Image-Edit-2509 is support for multi-image inputs. Let’s first look at a "person + person" example: Here is a "person + scene" example: Below is a "person + object" example: In fact, multi-image input also supports commonly used ControlNet…
This September, we are pleased to introduce Qwen-Image-Edit-2509, the monthly iteration of Qwen-Image-Edit. To experience the latest model, please visit Qwen Chat and select the "Image Editing" feature. Compared with Qwen-Image-Edit released in August, the main improvements of Qwen-Image-Edit-2509 include: Install the latest version of diffusers The following contains a code snippet illustrating how to use Qwen-Image-Edit-2509: The primary update in Qwen-Image-Edit-2509 is support for multi-image inputs. Let’s first look at a "person + person" example: Here is a "person + scene" example: Below is a "person + object" example: In fact, multi-image input also supports commonly used ControlNet…
FLUX 3 Image Klein is a 5.6B open weights model for text-to-image generation and image editing. It takes a prompt and up to 10 reference images and returns one image. Text-to-image, single-reference edits and multi-reference compositions run through the same model, with Qwen3-VL-4B-Instruct as the text encoder. The 5.6B parameter label refers to the image transformer; the text encoder is separate. This repository holds the distilled checkpoint for generation and image editing. For fine-tuning, LoRA training and research, use FLUX 3 Image Klein Base. Inference code, prompt upsampling and the bounding box format: black-forest-labs/flux-3-image-klein on GitHub. Do not use the model without a…
FLUX 3 Image Klein is a 5.6B open weights model for text-to-image generation and image editing. It takes a prompt and up to 10 reference images and returns one image. Text-to-image, single-reference edits and multi-reference compositions run through the same model, with Qwen3-VL-4B-Instruct as the text encoder. The 5.6B parameter label refers to the image transformer; the text encoder is separate. This repository holds the undistilled base checkpoint, for fine-tuning, LoRA training and research. You can find the distilled checkpoint here: FLUX 3 Image Klein. Inference code, prompt upsampling and the bounding box format: black-forest-labs/flux-3-image-klein on GitHub. Do not use the model…
Qwen-Image-2.1 on a 0.8B text encoder. Text-to-image, character and scene editing, and transparent (RGBA) generation in one pipeline. The text encoder is replaced by Qwen3.5-0.8B plus a 158M adapter, fine-tuned to reproduce what the native encoder produced — both from plain text and from text read together with the reference images (Improved using Qwen). The adapter lives inside the DiT as its text-fusion block, so the whole model is one self-contained diffusers folder and no 17.5 GB encoder is needed anywhere. The sampler runs a plain static shift of 5.0 instead of the original dynamic shifting. The bundled adapter is revision v12: its attention-branch position table covers 2304 slots and…