models/Sun]flower - v1.0

Sun]flower - v1.0

11/14/2025

12:46:58 AM

Related Keywords & Tags

fantasy art,flowers,illustration,ldworksdavid,lora,sdxl 1.0,sdxl lora,sdxl style lora,snfw3r,stable diffusion,style,sun]flower,sunflower,sunflower plant aesthetics,v1.0

Photorealistic ballet dancer posed on pointe with arms extended, wearing an intricately patterned dress forming a cascading Fibonacci spiral under chiaroscuro lighting.

Recommended Prompts

3d render,drawing,concept,illustration

Recommended Negative Prompts

low, bad, blurry, worse, worst, ugly, tiling, deformed, mutated, low quality

Recommended Parameters

samplers

DPM++ 2S a, DPM2 a

steps

cfg

resolution

1024x1024, 1024x768, 1024x1456, 512x768, 768x768, 1024x1456

other models

sd_xl_base_1.0_0.9vae (e6bb9ea85b)

Tips

Use trigger 'snfw3r' to activate the model.

Recommended weight is 1; reduce to 0.6 or lower if sunflower presence is too dominant.

Prompt guidance with styles like '3d render' or 'drawing' enhances results.

Maintain simple prompts focused on the desired subject as the LORA excels in non-realistic images.

The model was trained on multiple styles including concept art, 3D render, illustration for style transfer.

Not tested on finetuned SDXL Dreambooth models; open for testing.

Resolution affects prompt guidance, consider using recommended resolutions.

Version Highlights

SDXL ver. 1.1

Creator Sponsors

For workflow resources visit Huggingface ComfyUI Workflow.

Support the creator on Patreon.

Hi!

Sorry for the lack of news but I have been doing lots and lots of training so I can understand better SDXL new architecture. I'm on it but for now I wanted to present (and after 2 weeks of heavy tunning) Sun]flower, a new SDXL LORA and my very first SDXL Style LORA.

Sun]flower is a SDXL LORA that has certain sunflower plant aesthetics and can be used in a lot of different ways. I have tested it in WebUI and ComfyUI... I'm not sure yet which one I liked most but the sample images I put here (except 2) are from ComfyUI, in the next days I will upload some Webui Sample images too.

- If you want to know how to prompt please refer to the sample images.

- Trigger is snfw3r

- Recommended weight is 1 but if you feel there are too much sunflower in the scene use 0.6 onwards. Depends a lot on the concept and seed.
- Resolution recommended 1024x1024 or 1024x768/1024x1456 and even 512x768 or 768x768. Resolution will guide too the prompt, remember this.

- You can guide more the AI towards the style using "3d render", "drawing", etc. Remember that now SDXL will follow much better prompt.

- This LORA is good for almost anything except probably realistic but try to maintain prompts simple as possible and focus on what you want to see.

- This LORA was trained in more than 1 style so it can transfer to concept, illustration, 3D render, etc. Guide it with your prompt.

- This LORA wasn't testted on finetunned XL Dreambooth models because I wanted to see the inner strenght of it. Feel free to test it wherever you want.

In the case you want my workflow:
https://huggingface.co/datasets/davizca87/C01nWorkflow/tree/main <- LOAD it via Json file in Comfyui

And that's all. As always, eternal gratitude for all people giving feedback here, in Discord and of course supporting us in Patreon!

Remember we are in SDXL territory and I'm not as versed as in SD 1.5 so feeback, positive or negative is very much welcome.

NOTE: I'm currently studying Prodigy IA3 LOKR but for now you will habe to deal with this adafactor optimizers.