SwarmUI Presets v50 - Bundle Coverage Dashboard

This is high quality 20 steps preset for ERNIE Image Base model. Preset uses ERNIE Image Base Quant FP8 Scaled model but you can use other base variants as well. Last updated 22 April 2026.

This is high quality 4 steps preset for ERNIE Image Turbo model. Preset uses ERNIE Image Turbo Quant FP8 Scaled model but you can use other base variants as well. Last updated 22 April 2026.

This is newest FLUX 2 Turbo LoRA preset. It is working with amazing speed and quality. If you get out of RAM error, add --no-cache to your backend args. Native resolution is 2048x2048 and it takes like 40 seconds on RTX 5090. This preset has better art quality compared to realism version.

This is newest FLUX 2 Turbo LoRA preset. It is working with amazing speed and quality. If you get out of RAM error, add --no-cache to your backend args. Native resolution is 2048x2048 and it takes like 40 seconds on RTX 5090. This preset has better art quality compared to realism version. This preset has lower quality and uses lower RAM and VRAM due to GGUF.

This is newest FLUX 2 Turbo LoRA preset. It is working with amazing speed and quality. If you get out of RAM error, add --no-cache to your backend args. Native resolution is 2048x2048 and it takes like 40 seconds on RTX 5090. This preset has better realism compared to HQ version.

This is newest FLUX 2 Turbo LoRA preset. It is working with amazing speed and quality. If you get out of RAM error, add --no-cache to your backend args. Native resolution is 2048x2048 and it takes like 40 seconds on RTX 5090. This preset has better realism compared to HQ version. This preset has lower quality and uses lower RAM and VRAM due to GGUF.

This is high quality 20 steps preset for FLUX 2 Klein Base model. You can do more steps and may increase quality slightly or change Sampler to Seeds 2. For image editing tasks, upload images into prompt section not use init image. It works like Qwen Image Edit. Preset uses FLUX Klein Base 9b Quant FP8 Scaled model but you can use other base variants as well. Last updated 22 April 2026.

This is high quality preset for FLUX 2 Klein distilled / turbo models. I did set as 8 steps but it can go as low as 4 steps. For image editing tasks, upload images into prompt section not use init image. It works like Qwen Image Edit. Preset uses FLUX Klein Distilled 9b Quant FP8 Scaled model but you can use other distilled / turbo variants as well. Last updated 22 April 2026.

This is a FLUX 2 Quality 1 tier. The difference vs Quality 2 is that, this one uses 2x slower sampler. That is why. The difference is minimal. Moreover you can increase step count to 40 for more quality.

This is a FLUX 2 Quality 2 tier. The difference vs Quality 1 is that, this one uses 2x faster sampler. That is why. The difference is minimal. Moreover you can increase step count to 40 for more quality.

FLUX Dev Models - Krea and SRPO as well: 20-40 Steps - Just change base model to FLUX Dev or FLUX Krea or FLUX SRPO. You can use GGUF models as well

Official FLUX Kontext Dev Edit Any Image

Use this preset to inpaint small areas as shown in tutorial video. Just directly apply when doing inpainting. It will only change inpainting Init Image related parameters. Set step count accordingly. For example when Init Image Creativity is set to 0.6, you need 7 steps do to actually 4 steps. E.g. Qwen Fast LoRA requires 4 steps. So set steps count to 7 in this case.

This is highest quality LTX2 Image to Video preset. You can make it 12 steps or 4 steps. 12 steps yields even better quality. Also you can reduce resolution to half and use LTX2 upscale preset. 2x upscale not very well working for image to video but still useable. I coded an extension to make it work. The preset is by default 121 frames and 5 seconds but you can increase frame count. Also we auto enable LTX 2 LoRA detailer and LTX 2 static fixing LoRA with 0.7 scale. You can increase or decrease their strength according to your needs. Last updated 27 January 2026.

This is highest quality LTX2 Text to Video preset. You can make it 12 steps or 4 steps. 12 steps yields even better quality. Also you can reduce resolution to half and use LTX2 upscale preset. It is useful to set your LTX2 model base resolution as 480x480, then generate and when you have a liked video, reuse parameters and apply LTX2 upscale preset. The preset is by default 121 frames and 5 seconds but you can increase frame count. Also we auto enable LTX 2 LoRA detailer with 0.7 scale. You can increase or decrease its strength according to your needs. Last updated 27 January 2026.

This is video upscale preset for LTX2. It really improves quality if you do this way. Lets say target resolution is 1280x720px. So generate video in 640x360px and then apply this preset. It improves quality. This preset always upscales 2x and only works on LTX 2 video. This preset also doesn't work with Image to Video workflow. Last updated 27 January 2026.

This is highest quality LTX2.3 Image to Video preset. You can make it 12 steps or 4 steps. 12 steps yields even better quality. Also you can set resolution to 1920x1080p natively. The preset is by default 121 frames and 5 seconds but you can increase frame count. No LoRA used yet and working great. Last updated 26 April 2026

This is highest quality LTX2.3 Text to Video preset. You can make it 12 steps or 4 steps. 12 steps yields even better quality. Also you can increase resolution to native 1920x1080p. No LoRAs used at the moment. Last updated 26 April 2026.

This is highest quality LTX2.3 Video to Video preset. You can make it 12 steps or 4 steps. 12 steps yields even better quality. Also you can set resolution to 1920x1080p natively. The preset is by default 121 frames and 5 seconds but set them according to your input video. You can change Init Image Creativity to increase change effect or reduce it. You can also use different Video to Video LoRAs. This LoRA can also add / remove / replace objects and also change style. Last updated 26 April 2026

This is a preset to do outpainting on images with FLUX Fill Dev model as shown in tutorial. Currently FLUX Fill Dev model is the very best to outpaint images without changing rest of the image. Outpaint images with small portions if you get errors. Try multiple different seeds if you don't get perfect results.

This is Qwen Image 2512 Model at 2656x2656 pixel realism preset and it makes extremely high-quality realistic images on trained Qwen Image models like self-trained Qwen Image LoRA or Qwen Image Fine Tuned model. This is 4 steps base + 4 steps upscale config. This significantly increases the realism with a little bit loss of fantastic prompts capability. You can increase the used realism LoRA strength to 0.8 for even further realism. 0.6 is working really good and balanced. Last updated 2026 January 1.

This is Qwen Image 2512 Model at 2656x2656 pixel realism preset and it makes extremely high-quality realistic images on trained Qwen Image models like self-trained Qwen Image LoRA or Qwen Image Fine Tuned model. This is 4 steps base + 4 steps upscale config. This significantly increases the realism with no loss of complex prompting capability. Last updated 2026 January 1.

This is fast Qwen Image Realism generation with Qwen Image 2512 model. Only 8 steps and CFG 1. It uses newest res_2s Sampler and beta57 Scheduler for realism. res_2s is 2x slower than euler but much better realism. With 2026 January 1, this preset massively upgraded.

This is ultra fast Qwen Image generation with Qwen 2512 model. It uses newest LoRA. Last updated at 2026 January 1.

This is fast Qwen Image Edit newest model 25-11 (like FLUX Kontext) with 12 steps. It supports up to 3 input images and this is an amazing model. We are using Qwen-Image-FP8-Lightning-4steps-V1.0-fp32 and it is working perfect to speed up.

This is Qwen Image Edit 2511 - 2656x2656 pixel realism preset and it makes extremely high quality realistic images. This preset is made for training your subject on Qwen Image Edit 2511 model. It yields excellent realism and quality and prompt following. The very best so far. Last update 2026 January 1.

This is Qwen Image 2656x2656 pixel realism preset and it makes extremely high-quality realistic images on trained Qwen Image models like self-trained Qwen Image LoRA or Qwen Image Fine Tuned model. This is 4 steps base + 4 steps upscale config. This significantly increases the realism with a little bit loss of fantastic prompts capability. You can increase the used realism LoRA strength to 0.8 for even further realism. 0.6 is working really good and balanced.

This is a preset to generate stylized UHD images with your Qwen trained models whether it is Qwen Image base or 2512 or Qwen Image Edit Plus 2509 or 2511 model. This preset does 12 steps base and 10 steps upscale into 2656x2656 pixels. This is slower than Tier 2 but higher quality.

This is a preset to generate stylized UHD images with your Qwen trained models whether it is Qwen Image base or 2512 or Qwen Image Edit Plus 2509 or 2511 model. This preset does 12 steps base and 4 steps upscale into 2656x2656 pixels.

SDXL Models Best Settings With Realism Negative Prompt

This is a realism oriented extremely high quality latent 2x upscale workflow that is tested with SD 1.5, SDXL, SD 3.5, FLUX, Qwen Image, Wan 2.1, Wan 2.2 image generation workflows and presets we have. For this to work, set everything with direct apply or reuse parameters, and then do direct apply this preset. E.g. 1024x1024 base resolution will become 2048x2048. It is fully dynamic and uses whatever you use as base.

Wan 2.1 FusionX & Self Forcing LoRA Text to Video
8-10 Steps

Wan 2.1 Image To Video Base Model: 20-50 Steps

Wan 2.1 LightX2V LoRA Image to Video: 4-10 Steps

Wan 2.1 Text To Video Base Model: 20-50 Steps

Wan 2.2 Image to Video No-LoRA Higher Quality Improved Workflow - 20 Steps or More. 16 FPS, 81 frames and first 4 frames trimmed. This is highest quality Image To Video. You can increase steps count if you wish for even better quality but it will be slow. RIFE 2x Frame interpolation enabled by default thus 5 seconds 32 FPS generated

Wan 2.2 Text to Video No-LoRA Higher Quality Improved Workflow - 20 Steps or More. 16 FPS, 81 frames and first 4 frames trimmed. This is highest quality Text To Video. You can increase steps count if you wish for even better quality but it will be slow. RIFE 2x Frame interpolation enabled by default thus 5 seconds 32 FPS generated

Generate amazing realistic images with Wan 2.2 - extremely fast for default 1280x720p (can do excellent 1920x1080p as well) resolution and realistic. Type prompt above <refiner>

Extremely efficient Wan2.2 Image To Video with A14B-Moe-Distill-Lightx2v base model. 4 steps only and fast. Increase to 8 steps if you want better quality. No LoRA needed. Default settings are 16 FPS and 81 frames with RIFE 2x frame interpolation enabled. Thus output is 5 seconds at 32 FPS.

Latest Wan 2.2 Text to Video lightning config. Uses latest speed up LoRAs with best samplers and schedulers setup. Only 4 steps total. You can increase step count to 8 if you wish. 16 FPS - 81 Frames default. RIFE 2x Frame interpolation also enabled by default so output is 32 FPS - 5 seconds.

This is Z-Image Base model best quality preset. It does 40 steps and 1024x1024px generation. I recommend you to enable Upscale Images 2X preset we have with this to get the best quality. So that it will generate 2048x2048 base resolution images and it works amazing. Last updated 27 January 2026.

This is top quality Z Image Turbo preset. It does 9 steps and 1.25 upscale with 9 more steps. Thus this is highest quality. It generates 1920x1920 pixel total resolution.

This is fast Z Image Turbo preset. It does 9 steps. It is a fast and high quality and generates 1536x1536 pixel total.