If you like my model, please hit the big green like button👍, write a review, and upload some images! It really motivates me! If it helps, I've just created a small bounty to motive you!
Version 5 is the best yet. Based on the amazing Animagine XL 4.0 which has character knowledge, poses, camera angles, expressions and emotions. I find the version "4.0" (not so much "Opt" or "Zero") to be quite artistic and magical with lighting and composition compared to other models based on Pony or Illustrious.
This realistic derivative preserves the artistry, makes the "photorealistic" tag work better, and improves hands and anatomy. It defaults more to anime and can do painting and artist styles too.
It is not perfect photorealism, but it will do 2.5D and semi-real, with occasional generations looking very photoreal indeed.
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!)
size: 1024 x 1408 (1536 often creates long body or long limbs)
negative: lowres, error, cropped, worst quality, low quality, low score, bad score, average score, (blurry, nsfw, explicit, nude)
realism trigger words: sunlight, shadow, photorealistic. Be careful, do not increase strength in ComfyUI too much with a short prompt, for example (photorealistic:1.5) will destroy the quality.
Version 5 has improved shadows and lighting, lots of keywords will get you a dark image very easily. For previous versions, you had to lower cfg, use a lora. These keywords help a little: (chiaroscuro, darkness, dark room, shadows, 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" as that was the only option.
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 - quite authentic, quite realistic, but quite noisy except with specific samplers.
v2 - improved photorealism but further from the Anim4gine base model.
v3 - I focused on improving the prompt following from the base model, face expressions and good 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. 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 a bit more horny than I'd like and needs strong prompting for male characters.
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.