Picasso Diffusion 1.1 Model Card
Title: Welcome to Scientific Fact World.
English version is here.
ใฏใใใซ
Picasso Diffusionใฏใ็ด7000GPUๆ้ใใใ้็บใใAIใขใผใใซ็นๅใใ็ปๅ็ๆAIใงใใ
ใฉใคใปใณในใซใคใใฆ
ใฉใคใปใณในใซใคใใฆใฏใใใจใฎใฉใคใปใณใน CreativeML Open RAIL++-M License ใซไพๅคใ้คใๅ็จๅฉ็จ็ฆๆญขใ่ฟฝๅ ใใใ ใใงใใ ไพๅคใ้คใๅ็จๅฉ็จ็ฆๆญขใ่ฟฝๅ ใใ็็ฑใฏๅตไฝๆฅญ็ใซๆชๅฝฑ้ฟใๅใผใใใญใชใใจใใๆธๅฟตใใใงใใ ๅถๅฉไผๆฅญใซใใๆนใฏๆณๅ้จใซใใไบบใจ็ธ่ซใใฆใใ ใใใ ่ถฃๅณใงๅฉ็จใใๆนใฏใใพใๆฐใซใใชใใฆใไธ่ฌๅธธ่ญใๅฎใใใไฝฟใใใ ใใใ
ๆณๅพใซใคใใฆ
ๆฌใขใใซใฏๆฅๆฌใซใฆไฝๆใใใพใใใใใใใฃใฆใๆฅๆฌใฎๆณๅพใ้ฉ็จใใใพใใ ๆฌใขใใซใฎๅญฆ็ฟใฏใ่ไฝๆจฉๆณ็ฌฌ30ๆกใฎ4ใซๅบใฅใใๅๆณใงใใใจไธปๅผตใใพใใ ใพใใๆฌใขใใซใฎ้ ๅธใซใคใใฆใฏใ่ไฝๆจฉๆณใๅๆณ175ๆกใซ็ งใใใฆใฟใฆใใ ๆญฃ็ฏใๅนๅฉ็ฏใซใ่ฉฒๅฝใใชใใจไธปๅผตใใพใใ่ฉณใใใฏๆฟๆฒผๅผ่ญทๅฃซใฎ่ฆ่งฃใๅพก่ฆงใใ ใใใ ใใ ใใใฉใคใปใณในใซใใใ้ใใๆฌใขใใซใฎ็ๆ็ฉใฏๅ็จฎๆณไปคใซๅพใฃใฆๅใๆฑใฃใฆไธใใใ
ไฝฟใๆน
ๆ่ปฝใซๆฅฝใใฟใใๆนใฏใใใกใใฎSpaceใใไฝฟใใใ ใใใ ใขใใซใฏsafetensorsๅฝขๅผใckptๅฝขๅผใใใใฆใณใญใผใใงใใพใใ
ไปฅไธใไธ่ฌ็ใชใขใใซใซใผใใฎๆฅๆฌ่ช่จณใงใใ
ใขใใซ่ฉณ็ดฐ
ใขใใซใฟใคใ: ๆกๆฃใขใใซใใผในใฎ text-to-image ็ๆใขใใซ
่จ่ช: ๆฅๆฌ่ช
ใฉใคใปใณใน: CreativeML Open RAIL++-M-NC License
ใขใใซใฎ่ชฌๆ: ใใฎใขใใซใฏใใญใณใใใซๅฟใใฆ้ฉๅใช็ปๅใ็ๆใใใใจใใงใใพใใใขใซใดใชใบใ ใฏ Latent Diffusion Model ใจ OpenCLIP-ViT/H ใงใใ
่ฃ่ถณ:
ๅ่ๆ็ฎ:
@InProceedings{Rombach_2022_CVPR, author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn}, title = {High-Resolution Image Synthesis With Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {10684-10695} }
ใขใใซใฎไฝฟ็จไพ
Stable Diffusion v2ใจๅใไฝฟใๆนใงใใ ใใใใใฎๆนๆณใใใใพใใใ๏ผใคใฎใใฟใผใณใๆไพใใพใใ
- Web UI
- Diffusers
Web UIใฎๅ ดๅ
Stable Diffusion v2 ใฎไฝฟใๆนใจๅใใใckptๅฝขๅผใใพใใฏsafetensorๅฝขๅผใฎใขใใซใใกใคใซใจyamlๅฝขๅผใฎ่จญๅฎใใกใคใซใใขใใซใใฉใซใใซๅ ฅใใฆใใ ใใใ ่ฉณใใใคใณในใใผใซๆนๆณใฏใใใกใใฎ่จไบใๅ็ งใใฆใใ ใใใ ใชใใxformersใใคใณในใใผใซใใ--xformers --disable-nan-checkใชใใทใงใณใใชใณใซใใใใจใใใใใใใพใใใใใงใชใๅ ดๅใฏ--no-halfใชใใทใงใณใใชใณใซใใฆใใ ใใใ
Diffusersใฎๅ ดๅ
๐ค's Diffusers library ใไฝฟใฃใฆใใ ใใใ
ใพใใฏใไปฅไธใฎในใฏใชใใใๅฎ่กใใใฉใคใใฉใชใใใใฆใใ ใใใ
pip install --upgrade git+https://github.com/huggingface/diffusers.git transformers accelerate scipy
ๆฌกใฎในใฏใชใใใๅฎ่กใใ็ปๅใ็ๆใใฆใใ ใใใ
from diffusers import StableDiffusionPipeline, EulerAncestralDiscreteScheduler
import torch
model_id = "alfredplpl/picasso-diffusion-1-1"
scheduler = EulerAncestralDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler")
pipe = StableDiffusionPipeline.from_pretrained(model_id, scheduler=scheduler, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "anime, masterpiece, a portrait of a girl, good pupil, 4k, detailed"
negative_prompt="deformed, blurry, bad anatomy, bad pupil, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands, bad hands, fused fingers, messy drawing, broken legs censor, low quality, mutated hands and fingers, long body, mutation, poorly drawn, bad eyes, ui, error, missing fingers, fused fingers, one hand with more than 5 fingers, one hand with less than 5 fingers, one hand with more than 5 digit, one hand with less than 5 digit, extra digit, fewer digits, fused digit, missing digit, bad digit, liquid digit, long body, uncoordinated body, unnatural body, lowres, jpeg artifacts, 3d, cg, text, japanese kanji"
images = pipe(prompt,negative_prompt=negative_prompt, num_inference_steps=20).images
images[0].save("girl.png")
ๆณจๆ:
- xformers ใไฝฟใใจๆฉใใชใใพใใ
- GPUใไฝฟใ้ใซGPUใฎใกใขใชใๅฐใชใไบบใฏ
pipe.enable_attention_slicing()ใไฝฟใฃใฆใใ ใใใ
ๆณๅฎใใใ็จ้
- ่ชๅทฑ่กจ็พ
- ใใฎAIใไฝฟใใใใใชใใใใใใ็บไฟกใใใใจ
- ็ปๅ็ๆAIใซ้ขใใๅ ฑ้
- ๅ
ฌๅ
ฑๆพ้ใ ใใงใชใใๅถๅฉไผๆฅญใงใๅฏ่ฝ
- ็ปๅๅๆAIใซ้ขใใๆ ๅ ฑใใ็ฅใๆจฉๅฉใใฏๅตไฝๆฅญ็ใซๆชๅฝฑ้ฟใๅใผใใชใใจๅคๆญใใใใใงใใใพใใๅ ฑ้ใฎ่ช็ฑใชใฉใๅฐ้ใใพใใใ
- ๅ
ฌๅ
ฑๆพ้ใ ใใงใชใใๅถๅฉไผๆฅญใงใๅฏ่ฝ
- ็ ็ฉถ้็บ
- Discordไธใงใฎใขใใซใฎๅฉ็จ
- ใใญใณใใใจใณใธใใขใชใณใฐ
- ใใกใคใณใใฅใผใใณใฐ๏ผ่ฟฝๅ ๅญฆ็ฟใจใ๏ผ
- DreamBooth ใชใฉ
- ไปใฎใขใใซใจใฎใใผใธ
- ๆฌใขใใซใฎๆง่ฝใFIDใชใฉใง่ชฟในใใใจ
- ๆฌใขใใซใStable Diffusionไปฅๅคใฎใขใใซใจใฏ็ฌ็ซใงใใใใจใใใงใใฏใตใ ใใใใทใฅ้ขๆฐใชใฉใง่ชฟในใใใจ
- Discordไธใงใฎใขใใซใฎๅฉ็จ
- ๆ่ฒ
- ็พๅคง็ใๅฐ้ๅญฆๆ ก็ใฎๅๆฅญๅถไฝ
- ๅคงๅญฆ็ใฎๅๆฅญ่ซๆใ่ชฒ้กๅถไฝ
- ๅ ็ใ็ปๅ็ๆAIใฎ็พ็ถใไผใใใใจ
- Hugging Face ใฎ Community ใซใใใฆใใ็จ้
- ๆฅๆฌ่ชใ่ฑ่ชใง่ณชๅใใฆใใ ใใ
ๆณๅฎใใใชใ็จ้
- ็ฉไบใไบๅฎใจใใฆ่กจ็พใใใใใชใใจ
- ๅ็ๅใใใฆใใYouTubeใชใฉใฎใณใณใใณใใธใฎไฝฟ็จ
- ๅ็จใฎใตใผใในใจใใฆ็ดๆฅๆไพใใใใจ
- ๅ ็ใๅฐใใใใใใชใใจ
- ใใฎไปใๅตไฝๆฅญ็ใซๆชๅฝฑ้ฟใๅใผใใใจ
ไฝฟ็จใใฆใฏใใใชใ็จ้ใๆชๆใฎใใ็จ้
- ใใธใฟใซ่ดไฝ (Digital Forgery) ใฏๅ
ฌ้ใใชใใงใใ ใใ๏ผ่ไฝๆจฉๆณใซ้ๅใใใใใ๏ผ
- ็นใซๆขๅญใฎใญใฃใฉใฏใฟใผใฏๅ ฌ้ใใชใใงใใ ใใ๏ผ่ไฝๆจฉๆณใซ้ๅใใใใใ๏ผ
- ไปไบบใฎไฝๅใ็กๆญใงImage-to-Imageใใชใใงใใ ใใ๏ผ่ไฝๆจฉๆณใซ้ๅใใใใใ๏ผ
- ใใใใค็ฉใ้ ๅธใใชใใงใใ ใใ (ๅๆณ175ๆกใซ้ๅใใใใใ๏ผ
- ใใใใๆฅญ็ใฎใใใผใๅฎใใชใใใใชใใจ
- ไบๅฎใซๅบใฅใใชใใใจใไบๅฎใฎใใใซ่ชใใชใใใใซใใฆใใ ใใ๏ผๅจๅๆฅญๅๅฆจๅฎณ็ฝชใ้ฉ็จใใใใใใ๏ผ
- ใใงใคใฏใใฅใผใน
ใขใใซใฎ้็ใใใคใขใน
ใขใใซใฎ้็
- ๆกๆฃใขใใซใๅคง่ฆๆจก่จ่ชใขใใซใฏใใใพใ ใซๆช็ฅใฎ้จๅใๅคใใใใฎ้็ใฏๅคๆใใฆใใชใใ
ใใคใขใน
- ๆกๆฃใขใใซใๅคง่ฆๆจก่จ่ชใขใใซใฏใใใพใ ใซๆช็ฅใฎ้จๅใๅคใใใใคใขในใฏๅคๆใใฆใใชใใ
ๅญฆ็ฟ
ๅญฆ็ฟใใผใฟ
Danbooruใชใฉใฎ็กๆญ่ปข่ผใตใคใใ้คใใๅฝๅ ๆณใซๆบๆ ใใใใผใฟใจใขใใซใ
ๅญฆ็ฟใใญใปใน
- ใใผใใฆใงใข: A100 80GB, V100
่ฉไพก็ตๆ
็ฌฌไธ่ ใซใใ่ฉไพกใๆฑใใฆใใพใใ
็ฐๅขใธใฎๅฝฑ้ฟ
- ใใผใใฆใงใขใฟใคใ: A100 80GB, V100
- ไฝฟ็จๆ้๏ผๅไฝใฏๆ้๏ผ: 7000
- ๅญฆ็ฟใใๅ ดๆ: ๆฅๆฌ
ๅ่ๆ็ฎ
@InProceedings{Rombach_2022_CVPR,
author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
title = {High-Resolution Image Synthesis With Latent Diffusion Models},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2022},
pages = {10684-10695}
}
*ใใฎใขใใซใซใผใใฏ Stable Diffusion v2 ใซๅบใฅใใฆๆธใใใพใใใ
- Downloads last month
- 114