Based on the amazing Animagine XL v4.0 which was trained from scratch on SDXL 1.0 Base for good character and style knowledge without loras. It is rather artistic and magical with lighting, shadows and composition. CagliostroLab have a discord too. I haven't used "Opt" or "Zero" in the mix, I don't like their style.

If you like v5, please hit the big grey 👍 button so it turns green, write a nice word in the review, and post images! It really motivates me to keep developing v6 beta!If you need inspiration, support artists who share prompts by dropping ❤️'s in the Animagine XL Realistic v5 Prompts Weekly Hall of Fame. Halls for previous model versions: v4, v3, v2, v1.

Nemo474 has kindly sponsored the model for three weeks! It seems to take 5000~6000 ⚡ per week to stay on the online generator, please bid a little if you can help us reach 200th place and stay available!

v5: steps: 25 cfg: 3.0 sampler: euler (reduces noise!) scheduler: auto/normal.
v4: steps: 25 cfg: 4.0 sampler: euler_a (increases detail!) scheduler: auto/normal.
v3: steps: 20 cfg: 2.0 sampler: dpmpp_2m scheduler: beta (reduces noise!)

I've attempted to preserve the artistry and prompt following, but improve realism and hands. It is not perfect photorealism, but it will do 2D artist styles, 2.5D, semi-real, and occasionally photorealism.

size for local generation: 1024 x 1344 (1536 often creates long body or long limbs)

v5 negative: ugly, blurry, lowres, worst quality

previous versions negative: lowres, error, cropped, worst quality, low quality, low score, bad score, average score, (blurry, nsfw, explicit, nude)

realism trigger words: sunlight, shadow, realistic, photorealistic, and photographic concepts like depth of field or photo background.

Don't use a camera name or the word painting unless you want an actual camera or framed painting. Don't use pony scores, score_8 etc. Don't prompt big/perfect eyes unless you want them enormous. It will follow your prompt!

In ComfyUI, do not increase strength too much, as (photorealistic:1.5) will destroy the quality. You can get better artist styles with "((photorealistic))" in the negative.

v5 has improved shadows and lighting, lots of keywords will get you a dark image very easily. For previous v1..v4, you had to lower cfg, use a lora, and keywords like (chiaroscuro, dark, shadow, darkness, dark room, dusk, night:1.2)

ComfyUI Workflow: I have uploaded a zip of the showcase images in PNG format for you to drag in ComfyUI workflows. It's called "Training Data" but you can drag each image into ComfyUI.

For the sample images for v5, I pasted in lots of messy junk prompts from the civitai highest rated gallery for this week. Don't take them as "instructions" on how to structure your prompt!

For better characters, Animagine recommends not starting the prompt with "masterpiece, high score, great score, absurdres realistic, photorealistic" and instead putting it at the end:

original prompting guide: https://cagliostrolab.net/posts/optimizing-animagine-xl-40-in-depth-guideline-and-update

Version History

v1 - very authentic to Animagine, but quite noisy except with specific samplers.

v2 - higher photorealism but drifted further from the Anim4gine base model.

v3 - I focused on improving the prompt following from the base model, face expressions and good enough photo-reality. Works with wider range of samplers, steps and cfg.

v4 - An improvement in anatomy, realism, highlights and shadows. It also follows closely to Animagine XL 4.0. Unfortunately more horny, use "safe" in the positive and (nsfw, explicit) in the negative.

v5 - Improved prompt following, shadow and light dynamic range, better artist style flexibility, and good anatomy and acceptable hands. It's still a bit more horny than I'd like but it's difficult when all the realism models excel at XXX.

v6 - The beta is currently too noisy and not magical enough, but it is better at styles, following and has excellent realism.

License

This model adopts the original CreativeML Open RAIL++-M License from Stability AI without any modifications or additional restrictions. The license terms remain exactly as specified in the original SDXL license, which includes:

✅ Permitted: Commercial use, modifications, distributions, private use
❌ Prohibited: Illegal activities, harmful content generation, discrimination, exploitation
⚠️ Requirements: Include license copy, state changes, preserve notices
📝 Warranty: Provided "AS IS" without warranties

Please refer to the original SDXL license for the complete and authoritative terms and conditions.