①
Steps: 20
CFG: 4.5
Sampler: Euler Ancestral
Scheduler: Beta, Karras
②
Steps: 8
CFG: 4.5
Sampler: Res 2s
Scheduler: Beta, Karras
- Light & Skin Detail: The model excels at rendering realistic lighting and highly detailed skin textures, especially when the shiny skin tag is enabled.
- Post‑Processing Boost: Though the first pass using resolutions like 832×1216 may seem modest, applying I2I 1.5 × upscale and Facedetailer instantly transforms the image into a stunning result, dramatically enhancing sharpness, color depth, and skin gloss.
- The character’s hands sometimes appear inconsistent or less refined; a secondary refinement tool or node may help stabilize those details.
- After rigorous testing, FrancoIL not only shines at the conventional SDXL resolutions like 832×1216, but it also scales gracefully to larger canvases such as 1248×1824 -- where the first pass delivers a markedly richer and sharper result.
Feel free to adjust the settings to suit your workflow. Both 20‑step Euler and 8‑step Res‑2s approaches yield excellent outputs after the recommended upscaling and detail enhancement.
FrancoIL is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user FranChen. Derived from the powerful Stable Diffusion (Illustrious) model, FrancoIL has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that FrancoIL is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, digital art, base model.
With a rating of 0 and over 0 ratings, FrancoIL is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of FrancoIL from here.
To use FrancoIL, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like FrancoIL, check out our crash course in AI image generation.
v1.0 - based on our beloved wai IL v15
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.