yorgash/Flux Kontext workflow - detailers, IPAdapter, upscale, all optional
About the workflow: Nodes you will probably want to adjust and use normally. Init Load the pictures to be used with Kontext. Loader Select the diffusion model to be used, as well as load CLIP, VAE and select latent size for the generation. Prompt Pretty straight forward: your prompt goes here. Switches Basically the "configure" group. You can enable / disable model sampling, LoRAs, detailers, upscaling, automatic prompt tagging, clip vision UNClip conditioning and IPAdapter. I'm not sure how well those last two work, but you can play around with them. Model settings Model sampling and loading
| Author / organization | yorgash |
|---|---|
| Downloads | 5K (as reported by Civitai) |
| Likes | 153 |
| Task | text-to-image |
| Created | 12 July 2025 |
| Last updated at source | — |
Popularity, last 3 days
5,034 now (+7 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.
More from yorgash
- yorgash/SDXL LoRA trainer - auto set up, only need image folderModel
- yorgash/QWEN Image Edit 2511 Segment Inpaint, swap, local editModel
- yorgash/WAN2.2 SVI v2.0 Pro Simplicity - infinite prompt, separate prompt lengthsModel
- yorgash/QWEN Image Edit - Ultimate 2509 editModel
- yorgash/Flux.2 Klein / Ultimate AIO Pro (t2i, i2i, Inpaint, replace, remove, swap, edit) Segment (manual / auto / none)Model
- yorgash/WAN 2.2 I2V - Simple multiple prompt/video loopModel
Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.