diff --git a/.gitattributes b/.gitattributes index 97aa060cda9ad3b66fa6d3feadb4cad405821923..6cc2b9a712d9d0a93bea9f8789c9b4ae7518f6c2 100644 --- a/.gitattributes +++ b/.gitattributes @@ -590,3 +590,17 @@ Stable-diffusion/landuoAnima_v011_2566279.preview.png filter=lfs diff=lfs merge= Stable-diffusion/rdbtAnima_previewFp8_2538324.preview.png filter=lfs diff=lfs merge=lfs -text Stable-diffusion/rdbtAnima_rdbtV012fd_2598321.preview.png filter=lfs diff=lfs merge=lfs -text Stable-diffusion/sanicanima_v1_2626053.preview.png filter=lfs diff=lfs merge=lfs -text +Anima/anima_preview_2542128.preview.png filter=lfs diff=lfs merge=lfs -text +Anima/animaika_v10.preview.png filter=lfs diff=lfs merge=lfs -text +Anima/animaika_v20.preview.png filter=lfs diff=lfs merge=lfs -text +Anima/animaika_v21.preview.png filter=lfs diff=lfs merge=lfs -text +Anima/animaika_v22.preview.png filter=lfs diff=lfs merge=lfs -text +Anima/animayume_v01_2568787.preview.png filter=lfs diff=lfs merge=lfs -text +Anima/animayume_v02_2640368.preview.png filter=lfs diff=lfs merge=lfs -text +Anima/anyAnimayumeForLora_020_2646771.preview.png filter=lfs diff=lfs merge=lfs -text +Anima/btmx_v10.preview.png filter=lfs diff=lfs merge=lfs -text +Anima/harmoniqmixAnima_v01PreviewVersion_2566993.preview.png filter=lfs diff=lfs merge=lfs -text +Anima/landuoAnima_v011_2566279.preview.png filter=lfs diff=lfs merge=lfs -text +Anima/rdbtAnima_previewFp8_2538324.preview.png filter=lfs diff=lfs merge=lfs -text +Anima/rdbtAnima_rdbtV012fd_2598321.preview.png filter=lfs diff=lfs merge=lfs -text +Anima/sanicanima_v1_2626053.preview.png filter=lfs diff=lfs merge=lfs -text diff --git a/Anima/Put Stable Diffusion checkpoints here.txt b/Anima/Put Stable Diffusion checkpoints here.txt new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/Anima/anima_preview_2542128.html b/Anima/anima_preview_2542128.html new file mode 100644 index 0000000000000000000000000000000000000000..5b03f0aa9702d42f68cd7655d4094157a39fee23 --- /dev/null +++ b/Anima/anima_preview_2542128.html @@ -0,0 +1,241 @@ + +
+ + + + +
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
This is not my model. Don't ask me questions. I don't know the answers.
Go to the official Anima Huggingface repo for answers.
You need to use qwen_3_06b_base.safetensors for text encoder, and qwen_image_vae.safetensors for VAE.
I've only uploaded the model here as a way to tag the images I generate with it. It will most likely be taken down once the official owners upload their own version, so be warned.
The following is the original README as of time of publishing.
Anima is a 2 billion parameter text-to-image model created via a collaboration between CircleStone Labs and Comfy Org. It is focused mainly on anime concepts, characters, and styles, but is also capable of generating a wide variety of other non-photorealistic content. The model is designed for making illustrations and artistic images, and will not work well at realism.
It is trained on several million anime images and about 800k non-anime artistic images. No synthetic data was used for training. The knowledge cut-off date for the anime training data is September 2025.
This preview version is an intermediate model checkpoint. The model is still training and the final version will improve, especially for fine details and overall aesthetics.
The model is natively supported in ComfyUI. The above image contains a workflow; you can open it in ComfyUI or drag-and-drop to get the workflow. The model files go in their respective folders inside your model directory:
anima-preview.safetensors goes in ComfyUI/models/diffusion_models
qwen_3_06b_base.safetensors goes in ComfyUI/models/text_encoders
qwen_image_vae.safetensors goes in ComfyUI/models/vae (this is the Qwen-Image VAE, you might already have it)
The preview version should be used at about 1MP resolution. E.g. 1024x1024, 896x1152, 1152x896, etc.
30-50 steps, CFG 4-5.
A variety of samplers work. Some of my favorites:
er_sde: neutral style, flat colors, sharp lines. I use this as a reasonable default.
euler_a: Softer, thinner lines. Can sometimes tend towards a 2.5D look. CFG can be pushed a bit higher than other samplers without burning the image.
dpmpp_2m_sde_gpu: similar in style to er_sde but can produce more variety and be more "creative". Depending on the prompt it can get too wild sometimes.
The model is trained on Danbooru-style tags, natural language captions, and combinations of tags and captions.
[quality/meta/year/safety tags] [1girl/1boy/1other etc] [character] [series] [artist] [general tags]
Within each tag section, the tags can be in arbitrary order.
Human score based: masterpiece, best quality, good quality, normal quality, low quality, worst quality
PonyV7 aesthetic model based: score_9, score_8, ..., score_1
You can use either the human score quality tags, the aesthetic model tags, both together, or neither. All combinations work.
Specific year: year 2025, year 2024, ...
Period: newest, recent, mid, early, old
highres, absurdres, anime screenshot, jpeg artifacts, official art, etc
safe, sensitive, nsfw, explicit
Prefix artist with @. E.g. "@big chungus". You must put @ in front of the artist. The effect will be very weak if you don't.
year 2025, newest, normal quality, score_5, highres, safe, 1girl, oomuro sakurako, yuru yuri, @nnn yryr, smile, brown hair, hat, solo, fur-trimmed gloves, open mouth, long hair, gift box, fang, skirt, red gloves, blunt bangs, gloves, one eye closed, shirt, brown eyes, santa costume, red hat, skin fang, twitter username, white background, holding bag, fur trim, simple background, brown skirt, bag, gift bag, looking at viewer, santa hat, ;d, red shirt, box, gift, fur-trimmed headwear, holding, red capelet, holding box, capelet
The model was trained with random tag dropout. You don't need to include every single relevant tag for the image.
To improve style and content diversity, the model was additionally trained on two non-anime datasets: LAION-POP (specifically the ye-pop version) and DeviantArt. Both were filtered to exclude photos. Because these datasets are qualitatively different from anime datasets, captions from them have been labeled with a "dataset tag". This occurs at the very beginning of a prompt followed by a newline. Optionally, the second line can contain either the image alt-text (ye-pop) or the title of the work (DeviantArt). Examples:
ye-pop
For Sale: Others by Arun Prem
Abstract, oil painting of three faceless, blue-skinned figures. Left: white, draped figure; center: yellow-shirted, dark-haired figure; right: red-veiled, dark-haired figure carrying another. Bold, textured colors, minimalist style.
deviantart
Flame
Digital painting of a fiery dragon with glowing yellow eyes, black horns, and a long, sinuous tail, perched on a glowing, molten rock formation. The background is a gradient of dark purple to orange.
If using pure natural langauge, more descriptive is better. Aim for at least 2 sentences. Extremely short prompts can give unexpected results (this will be better in the final version).
You can mix tags and natural language in arbitrary order.
You can put quality / artist tags at the beginning of a natural language prompt.
"masterpiece, best quality, @big chungus. An anime girl with medium-length blonde hair is..."
Name a character, then describe their basic appearance.
"Digital artwork of Fern from Sousou no Frieren, with long purple hair and purple eyes, wearing a black coat over a white dress with puffy sleeves..."
This is extra important when prompting for multiple characters. If you just list off character names with no description of appearance, the model can get confused.
You may be interested in comparing Anima's outputs with other models. A ComfyUI workflow, anima_comparison.json, is provided. This workflow generates a grid of images where each model is a column and the rows are different seeds. It can be configured to compare any number of models you select by changing a few output nodes. Supported model architectures: Anima, SDXL, Lumina, Chroma, Newbie-Image. The default configuration compares Anima, NetaYume, and Newbie-Image.
The model doesn't do realism well. This is intended. It is an anime / illustration / art focused model.
The model may generate undesired content, especially if the prompt is short or lacking details.
Avoid this by using the appropriate safety tags in the positive and negative prompts, and by writing sufficiently detailed prompts.
The model isn't great at text rendering. It can generally do single words and sometimes short phrases, but lengthy text rendering won't work well.
The preview model isn't that good at higher resolutions yet.
It is a medium-resolution intermediate checkpoint, trained on a small amount of high-res images.
The final version will have been trained on a dedicated high-res phase. Details and overall image composition will improve.
The preview model is a true base model. It hasn't been aesthetic tuned on a curated dataset. The default style is very plain and neutral, which is especially apparent if you don't use artist or quality tags.
This model is licensed under the CircleStone Labs Non-Commercial License. The model and derivatives are only usable for non-commercial purposes. Additionally, this model constitutes a "Derivative Model" of Cosmos-Predict2-2B-Text2Image, and therefore is subject to the NVIDIA Open Model License Agreement insofar as it applies to Derivative Models.
The details of the commercial licensing process are still being worked out. For now, you can express your interest in acquiring a commercial license by emailing tdrussell1@proton.me
Built on NVIDIA Cosmos.
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
AnimaYume is a text-to-image model fine-tuned from Anima, a high-quality anime-style image generation model developed by CircleStone Labs. It builds upon Cosmos 2, a model developed by NVIDIA’s research team.
For version 0.1:
This model is a preview version fine-tuned from the Anima base model using a custom dataset. Training was conducted across multiple resolutions ranging from 768 to 1280 pixels, with a primary focus around 1024. The goal of this release is to improve stability and minimize unwanted artifacts when producing high-resolution images.
Notes: All the example images at this version were generated at the resolution 1024x1536 or 1536x1024
For version 0.2:
This model is a continuation of AnimeYume v0.1. In this version, I improved the quality of my dataset and used several techniques to prevent oversaturation and low-quality outputs. Based on my testing phase, I observed that the prompt coherence is better than v0.1, and the model remains very stable when generating images at a resolution of 1536.
Note: I am still waiting for the final version of Anima and testing some methods to make my training process faster. I know the license might make the model less popular, but I only care about whether the model is good or not. I’m aware that many others use better licenses, but I’m too lazy to spend a bunch of money training a model from scratch.
This file contains only the diffusion model and does not include a VAE or text encoder. To use it properly, you will need to download those components from the link here
This is an experimental fine-tuned release, and I am waiting for the final version release to tune it :D
Your feedback, suggestions, and creative prompt ideas are always welcome, every contribution helps make this model even better!
Big thanks to narugo1992 for the dataset contributions.
Credit to Circlestone Labs and Nvidia for the fantastic base model architecture.
If you'd like to support my work, you can do so through Ko-fi!
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
AnimaYume is a text-to-image model fine-tuned from Anima, a high-quality anime-style image generation model developed by CircleStone Labs. It builds upon Cosmos 2, a model developed by NVIDIA’s research team.
For version 0.1:
This model is a preview version fine-tuned from the Anima base model using a custom dataset. Training was conducted across multiple resolutions ranging from 768 to 1280 pixels, with a primary focus around 1024. The goal of this release is to improve stability and minimize unwanted artifacts when producing high-resolution images.
Notes: All the example images at this version were generated at the resolution 1024x1536 or 1536x1024
For version 0.2:
This model is a continuation of AnimeYume v0.1. In this version, I improved the quality of my dataset and used several techniques to prevent oversaturation and low-quality outputs. Based on my testing phase, I observed that the prompt coherence is better than v0.1, and the model remains very stable when generating images at a resolution of 1536.
Note: I am still waiting for the final version of Anima and testing some methods to make my training process faster. I know the license might make the model less popular, but I only care about whether the model is good or not. I’m aware that many others use better licenses, but I’m too lazy to spend a bunch of money training a model from scratch.
This file contains only the diffusion model and does not include a VAE or text encoder. To use it properly, you will need to download those components from the link here
This is an experimental fine-tuned release, and I am waiting for the final version release to tune it :D
Your feedback, suggestions, and creative prompt ideas are always welcome, every contribution helps make this model even better!
Big thanks to narugo1992 for the dataset contributions.
Credit to Circlestone Labs and Nvidia for the fantastic base model architecture.
If you'd like to support my work, you can do so through Ko-fi!
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Modified Animayume for LoRA training.
It reduces unintended style changes.
Note: This model is not suitable for image generation. The model tends to generate ugly images.
LoRA学習用のAnimayumeです。
意図しない画風の変化を軽減し、精度も改善します。
Dataset size: 5120
Gelbooruから収集した5120枚の画像で学習しました。
なお、以下のタグがあるか条件を満たす画像は除外しました。
filetype:gif, score:<0, mpixels:<1048576, tagcount:<16, \*_artifacts, adversarial_noise, greyscale, monochrome, digimon, photophop_(meidum), ai-generated, duplicate, bad_\*, off-topic, cropped, resized, reversed, rotated, third-party_edit, screenshot, tagme, real_life, watermark, 3d, koikatsu_(medium), mikumikudance, twitter_username
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
resolution
1024x1024, 896x1152, 1152x896, etc.
steps
30~50
CFG
3.0 ~ 5.0
Quality tag
masterpiece, best quality, good quality, highly detailed, highres, absurdres, newestNegative tag
worst quality, low quality, old, oldestThis model is a derivative of the CircleStone Model "Anima" and is distributed under the CircleStone Labs Non-Commercial License.
The base model (Anima) and its derivatives are for non-commercial use only.
If you need commercial use, you must obtain a separate commercial license from CircleStone Labs.
Outputs (generated images) may be used for commercial purposes, but you may not use outputs to train/fine-tune/distill a model that is competitive with a CircleStone model.
This model includes modifications to the CircleStone Model by hybskgks28275.
Modification type: Merged checkpoint (LoRA weights merged into AnimaYume base checkpoint)
Base model: Anima Preview
This derivative is not an official product of CircleStone Labs LLC and is not endorsed, approved, or validated by CircleStone Labs LLC.
A copy of the attribution notice is included as NOTICE.txt.

Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
This is a test model.
Better prompts
masterpiece, best quality, newest, score_9, score_8, {prompts}, {Natural Language}.Negative prompts
worst quality, low quality, score_1, score_2, score_3, blurry, jpeg artifacts, sepia,This model merges Anima-preview with LoRA trained using self-generated images.
The example images were generated using LoRA, so please omit LoRALoader for reference.
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
This page contains RDBT checkpoint model, in fp16 and fp8. Also a fp8 "anima preview", just for convenience.
RDBT [fp16 + fp8]
Finetuned anima preview. More info: https://civitai.com/models/2364703
Note:
It's distilled model and needs different settings. Read the docs above!
The RDBT model was trained as a fp32 LoRA natively. If you already have the "preview" anima base model, you can just download and load the LoRA.
If you don't know what this means, or which one is the right "base model", you can download and use this fp16 checkpoint model, which has merged the LoRA.
Restrictions: Making merges using this model is not allowed. FYI, this model was trained with latent watermark.
preview [fp8]:
fp8 anima preview
About fp8 models:
Quantized fp8 models in ComfyUI format.
Model file contains calibrated metadata for hardware fp8 linear. If you GPU supports it (aka. rtx 4000 and later), ComfyUI will use hardware fp8 automatically, which might (blame Nvidia) be a little bit faster. More about ComfyUI fp8, see ComfyUI docs TensorCoreFP8Layout.
Just ignore ComfyUI log warnings about tons of keys not loaded. Its a small bug in ComfyUI, it checked wrong keys. Those keys are metadata and they are loaded.
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
This page contains RDBT checkpoint model, in fp16 and fp8. Also a fp8 "anima preview", just for convenience.
RDBT [fp16 + fp8]
Finetuned anima preview. More info: https://civitai.com/models/2364703
Note:
It's distilled model and needs different settings. Read the docs above!
The RDBT model was trained as a fp32 LoRA natively. If you already have the "preview" anima base model, you can just download and load the LoRA.
If you don't know what this means, or which one is the right "base model", you can download and use this fp16 checkpoint model, which has merged the LoRA.
Restrictions: Making merges using this model is not allowed. FYI, this model was trained with latent watermark.
preview [fp8]:
fp8 anima preview
About fp8 models:
Quantized fp8 models in ComfyUI format.
Model file contains calibrated metadata for hardware fp8 linear. If you GPU supports it (aka. rtx 4000 and later), ComfyUI will use hardware fp8 automatically, which might (blame Nvidia) be a little bit faster. More about ComfyUI fp8, see ComfyUI docs TensorCoreFP8Layout.
Just ignore ComfyUI log warnings about tons of keys not loaded. Its a small bug in ComfyUI, it checked wrong keys. Those keys are metadata and they are loaded.
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
SanicAnima is fast Anima model.
The Full model is a checkpoint (AIO) model and the Pruned model is a diffusion model. If you know how to use the Anima model, use the Diffusion model. Otherwise, use the Checkpoint (AIO) model.
The recommended settings are: dpmpp_2m_sde_gpu / simple / CFG 2.5 / 15 Stpes
For detailed usage instructions, please refer to the metadata of the sample images and the Anima Readme document.
+