Distilling Diffusion Models
Shreshth Saini · Sep 2026
shreshthsaini.github.io/blogs/diffusion-distillation.html
50 steps
4 steps
[1] Yin et al. 2024, CC BY 4.0
What we will cover today
2
What is the student allowed to forget?
1
Why diffusion
is slow
2
What distillation is
3
Three things a
student can copy
4
Copy the
teacher's path
5
Match the teacher's
distribution
6
Distilling
video models
7
What still
breaks
Part 1
Why diffusion is slow
Why does one image need a hundred network passes?
Sampling takes many small steps
4
[1] Yin et al. 2024, arXiv:2405.14867 · [49] Team Wan 2025, arXiv:2503.20314
noise, t = 1
image x₀, t = 0
every dot is one forward pass
the probability-flow ODE
cost per sample = NFE × network cost
From 100 network passes down to 4
5
[1] Yin et al. 2024, arXiv:2405.14867 · [19] Huang et al. 2025, arXiv:2506.08009 · [49] Team Wan 2025, arXiv:2503.20314
teacher
50 steps × 2 for guidance = 100 passes
student
1 to 4 passes
distillation
25 to 100 times fewer
Wan2.1 1.3B takes 103 s for one clip on an H100.
Why one big step gives a blur
6
noisy input
a cat
a dog
half cat, half dog
the one-step answer
This noise could become a cat or a dog.
Asked to answer in one step, the network returns the average, a blur.
One step lands on the average image
7
data
cat
dog
low noise
xₜ
average
mid noise
xₜ
high noise
xₜ
the blur, between the peaks
Squared-error training learns this average.
Part 2
What distillation is
How does a student learn from a teacher?
Distillation in one picture
9
[7] Hinton et al. 2015, arXiv:1503.02531
label
BMW
truck
carrot
teacher
BMW
truck
carrot
student
BMW
truck
carrot
match
The label says BMW. The teacher says BMW, a bit garbage truck, almost no carrot.
The student learns from that extra shape.
Language models went through this first
10
2015
Soft targets
Hinton
2016
Sequence-level KD
Kim and Rush
2024
Reverse KL
2024
Student rollouts
Trajectory matching
on teacher states
on student samples
on student rollouts
language models
diffusion
off-policy
on-policy
the student starts sampling here
In diffusion, the student learns to skip steps
11
[6] Salimans and Ho 2022, arXiv:2202.00512
Teacher
Student
copied weights
t = 1
t = 0
every noise level
just 1 to 4 levels run
Why diffusion is harder to distill
12
x₀
50 steps
?
No few-step answer key
ε(xₜ, c)
ε(xₜ, ∅)
γ
student, fixed γ
Guidance is in the target
encoder
teacher
student
loss
latent
decoder
The VAE sits outside
×
student
fake score
real score
Video needs more memory
Who sets the target, and on what samples
13
Off-policy
trained on data or teacher states
On-policy
trained on the student's own samples
Teacher distillation
target from a frozen teacher
Self-distillation
target from its own output
also called teacher-free
consistency training
rare
on-policy still
has a teacher
Learning to drive, three ways
14
off-policy
Watch the instructor drive.
on-policy
Drive while the instructor
corrects you.
self-distillation
Or check your answer against
your own later answer.
consistency training, MeanFlow
instructor
student watches
student
instructor
correction
student
you, later
own target
still has a teacher
Forward KL spreads, reverse KL picks a peak
15
forward KL, the teacher's loss
data p
fit q
reverse KL, the student's loss
data p
fit q
skipping this mode costs nothing
A student can beat its teacher on FID while covering less.
Part 3
Three things a student can copy
What exactly does the student try to match?
Three ways to learn to draw
17
trace
Trace the teacher's strokes.
trajectory
match the stack
Make your whole stack of
drawings look like theirs.
distribution
critic
Or let a critic call each
one real or fake.
discriminator
drawing
critic
real
fake
Every method copies one of three things
18
[27] Song et al. 2023, arXiv:2303.01469 · [40] Yin et al. 2024, arXiv:2311.18828 · [44] Sauer et al. 2023, arXiv:2311.17042
trajectory
a point
distribution
a density
discriminator
a verdict
teacher step
student
loss
noise
data
real
fake
score difference
student
real or
teacher-made
D
real
fake
Part 4
Copy the teacher's path
How did the first methods cut the steps?
Learning to skip stairs
20
Learn to cover two of the teacher's steps in one.
Then the student becomes the teacher.
Repeat: 8, 4, 2, 1.
teacher
4
2
1
8
steps
one round of training each
Progressive distillation halves the steps each round
[6] Salimans and Ho 2022, arXiv:2202.00512
21
teacher distillation, off-policy
steps
CIFAR-10 FID
8
2.57
4
3.00
2
4.51
1
9.12
two teacher steps
one student step
each student becomes
the next teacher
one student step
two teacher DDIM steps
MSE
Guidance distillation folds two passes into one
[20] Meng et al. 2023, arXiv:2210.03142
22
teacher distillation, off-policy
teacher, two evaluations
student, one evaluation
guided target
MSE
evaluations per sample
2N
N
N/2, N/4, …
FID: guided teacher 9.84, one-step student 7.54
ImageNet 64, w = 1
the student beats its teacher
The idea behind consistency models
23
noise
the teacher's path
image
must agree
From any point on the trip, say where it ends.
Two nearby points must give the same answer.
A consistency model jumps straight to the image
[27] Song et al. 2023, arXiv:2303.01469
24
noise
data
ODE trajectory
identity here, by construction
same trajectory, same output
Consistency distillation makes neighbours agree
[27] Song et al. 2023, arXiv:2303.01469
25
teacher distillation, off-policy
consistency loss
noise
data
teacher ODE step
EMA copy, stop-grad
noised real data,
so off-policy
FID | 1 step | 2 steps | teacher |
CD, CIFAR-10 | 3.55 | 2.93 | 2.04 |
CD, ImageNet 64 | 6.20 | 4.70 | 2.44 |
Consistency training drops the teacher
[27] Song et al. 2023, arXiv:2303.01469 · [28] Song and Dhariwal 2024, arXiv:2310.14189 · [30] Lu and Song 2025, arXiv:2410.11081
26
self-distillation (teacher-free), off-policy
Method | Teacher | Benchmark | 1-step FID | 2-step FID |
CD, 2023 | EDM | CIFAR-10 | 3.55 | 2.93 |
CT, 2023 | none | CIFAR-10 | 8.70 | 5.83 |
iCT-deep, 2024 | none | CIFAR-10 | 2.51 | 2.24 |
sCT-XXL, 2025 | none | ImageNet 512 | 4.29 | 3.76 |
no teacher, and
it beats CD
LCM brought four steps to Stable Diffusion
[24] Luo et al. 2023, arXiv:2310.04378
27
teacher distillation, off-policy
LCM FID, 512px
35.36
1
13.31
2
11.10
4
11.84
8
steps
the four-step default
Reflow straightens the path
[31] Liu et al. 2022, arXiv:2209.03003 · [32] Liu et al. 2024, arXiv:2309.06380
28
teacher distillation, off-policy
1-rectified flow
noise
image
one Euler step misses
2-rectified flow
noise
image
one Euler step lands
On SD 1.5, InstaFlow gets FID 23.4 in one step, against the teacher's 20.1.
the price of a straight path
Flow maps learn whole jumps at once
[34] Geng et al. 2025, arXiv:2505.13447 · [33] Frans et al. 2025, arXiv:2410.12557
29
self-distillation, off-policy
instantaneous velocity
average velocity
noise
data
trajectory
one jump, no solver
MeanFlow identity
Shortcut models make one 2d step match two of their own d steps.
The trouble with copying the path
30
one step blurs
every teacher error is copied
the teacher is the ceiling
keeps the noise-to-image pairing and variety
Part 5 starts here
One step on a curved path blurs
31
[32] Liu et al. 2024, arXiv:2309.06380 (MIT) · [6] Salimans and Ho 2022, arXiv:2202.00512, Fig. 3 · cropped
SD 1.5, 25 steps
InstaFlow, 1 step
straightened by reflow
Progressive distillation, curved path
256 steps
1 step
the average image, drawn
One-step scores kept getting better
32
teacher distillation
self-distillation
CIFAR-10, one step
FID, lower is better
2022
2023
2024
PD 9.12
CT 8.70
CD 3.55
iCT-deep 2.51
ImageNet 256, no teacher
FID, lower is better
2025
2026
multi-step SiT, 2.06
Shortcut 10.6
MeanFlow 3.43
AlphaFlow 2.58
DMF 2.16
iMF 1.72
no teacher anywhere
Part 5
Match the teacher's distribution
What if we judge the result and ignore the path?
Distribution matching in one picture
34
Push each student sample toward where the teacher's samples live, and away from where the student's own samples pile up.
teacher
student
real score
fake score
update = blue minus green
DMD moves samples by a score difference
[40] Yin et al. 2024, arXiv:2311.18828
35
fake score
trained online
real score
frozen teacher
z
G
x
gradient
on-policy, still
teacher distillation
DMD also needed teacher pairs
[40] Yin et al. 2024, arXiv:2311.18828
36
fake score
denoises G's samples
real score
frozen teacher
G(z)
teacher pair y
LPIPS
One step, FID | CIFAR-10 | ImageNet 64 |
regression only | 3.82 | 9.21 |
distribution only | 5.58 | 5.61 |
both | 2.66 | 2.62 |
mode collapse without pairs
DMD2 drops the pairs and adds a GAN
[1] Yin et al. 2024, arXiv:2405.14867
37
fake score
5 updates per step
real score
G
GAN head
real images
the only place real data enters
ImageNet 64, one step | FID |
2.62 | |
drop pairs | 3.48 |
+ 5 critic updates | 2.61 |
+ GAN head | 1.51 |
GAN only | 2.52 |
Four DMD2 steps next to fifty SDXL steps
[1] Yin et al. 2024, arXiv:2405.14867, Figs. 6 and 10 · images CC BY 4.0, cropped
38
SDXL, 50 steps, guidance
DMD2, 4 steps
50 steps
4 steps
FID 19.32 vs 19.36 · LPIPS diversity 0.61 vs 0.64
Moment matching in one picture
[75] Salimans et al. 2024, arXiv:2406.04103
39
Do not check each sample. At every noise level, make the student's average guess of the clean image match the teacher's.
one noise level t
teacher average
student average
match
Moment matching compares average predictions
[75] Salimans et al. 2024, arXiv:2406.04103, Fig. 1, cropped · CC BY-NC-SA 4.0
40
1
real image
+ noise → zₜ
2
student
x̃ = gη(zₜ)
3
sampler step
zₛ ~ q(zₛ | zₜ, x̃)
aux. denoiser
teacher
gradient
matched for every zₛ
starts from noised real data
ImageNet 64
8 steps 1.24
teacher 1.42
at 1024 steps
8-step text-to-image
A student can beat its teacher's score
[41] Zhou et al. 2024, arXiv:2404.04057 · [5] Dieleman 2024, sander.ai
41
teacher
student
recall drops
teacher
student
FID, lower is better
CIFAR-10
1.97
1.923
recall, higher is better
ImageNet 64
0.67
0.63
SiD, one step, against its EDM teacher
LADD judges images in the teacher's features
[44] Sauer et al. 2023, arXiv:2311.17042 · [45] Sauer et al. 2024, arXiv:2403.12015
42
noised image
Student, 4 steps
add noise
Teacher denoises
distillation loss
LADD drops this term
DINOv2 features, pixel space
real images
Teacher features, latent space
teacher samples
costs diversity
LADD
costs prompt alignment
Discriminator heads
adversarial loss
SDXL-Turbo at one, two and four steps
[44] Sauer et al. 2023, arXiv:2311.17042 · images CC BY 4.0, cropped
43
1 step
2 steps
4 steps
same seed
SDXL, 50 steps
SDXL-Turbo, 4 steps
What few-step images still get wrong
[74] Chen 2025, arXiv:2510.14974, Fig. 5 · [53] Zheng 2026, arXiv:2510.08431, Fig. 3 · [24] Luo 2023, arXiv:2310.04378, Fig. 5 · [6] Salimans 2022, arXiv:2202.00512, Fig. 3 · cropped
44
garbled
signs
pi-Flow, 8 NFE
FLUX Turbo, 8 NFE
wrong
digits
teacher
sCM 4-step
burnt
colour
LCM, w=4
w=12
one-step
blur
256 steps
1 step
Why distilled models lose variety
[63] Jiang et al. 2025, arXiv:2511.13649 · [1] Yin et al. 2024, arXiv:2405.14867
45
the loss picks a peak
reverse KL
teacher
student
guidance sharpens the target
ImageNet 256, one-step DMD
guidance | FID | recall |
none | 2.13 | 0.64 |
1.5 | 5.20 | 0.48 |
4 | 15.70 | 0.11 |
only guidance changed
New seed, same picture
[80] Wu et al. 2026, arXiv:2602.03139, Fig. 1 · panels cropped and relabelled
46
SD3.5-M teacher, 60 NFE
DMD, 4 NFE
DP-DMD, 4 NFE
One prompt, 25 seeds per grid
one face, 25 seeds
Newer methods keep more of the variety
47
Qwen-Image teacher
50x2 NFE
0.200
Qwen-Image-Lightning
labelled DMD2
0.095
0.150
0.182
PDD-Euler
0.192
OneIG diversity, 4 NFE, one evaluator
Base model takes step 1
DreamSim 0.264 to 0.350, base 0.337
DP-DMD's step 1, SDXL
DINOv3 0.109 to 0.173, base 0.219
What the big labs ship for images
[16] Chen 2025 · [36] Sabour 2025 · [46] Lin 2024 · [26] Ren 2024 · [107] Liu 2026 · [108] Black Forest Labs 2026
48
steps
family
NVIDIA
1 to 4
trajectory
discriminator
4 to 8
trajectory
ByteDance Seed
1 to 8
discriminator
1 to 8
trajectory
Nankai, Alibaba
CDM
4
distribution
Black Forest Labs
FLUX.2 [klein]
4
the card never says how
Part 6
Distilling video models
Why not run the image recipe on every frame?
Frame by frame, the video flickers
[49] Team Wan 2025, arXiv:2503.20314 · [19] Huang et al. 2025, arXiv:2506.08009 · [50] Yin et al. 2025, arXiv:2412.07772
50
Per-frame student
flicker
Chunk-wise student
steady
frames in a chunk share attention
time
Wan2.1-1.3B takes 100 passes over 21 latent frames, 103 s per clip on one H100.
A causal mask lets the student stream
[50] Yin et al. 2025, arXiv:2412.07772 · [19] Huang et al. 2025, arXiv:2506.08009
51
Bidirectional teacher
Block-causal student
Frame-causal student
keys
queries
sees later frames in its chunk
KV cache
one chunk per step
then the oldest drops
CausVid learns to stream from a bidirectional teacher
[50] Yin et al. 2025, arXiv:2412.07772
52
Bidirectional teacher
Causal student
same weights, block-causal mask
KV cache
Real score
Fake score
DMD loss
teacher
219.2 s
student
9.4 FPS
first frame at 1.3 s
Four streaming steps next to fifty teacher steps
[50] Yin et al. 2025, arXiv:2412.07772 · CC BY-NC-SA 4.0
53
bidirectional teacher, 50 steps
CausVid, 4 steps
0
1.3
2.6
3.9 s
Same prompt; the student streams from 1.3 s.
rCM keeps Wan2.1 sharp down to two steps
[53] Zheng et al. 2026, arXiv:2510.08431 · Apache-2.0
54
1 step
2 steps
4 steps
VBench
FPS
82.65
32.3
84.09
23.0
84.43
14.6
teacher, 50 steps, CFG
83.02
0.72
One step blurs the street.
Why small mistakes pile up in video
55
training
next
clean data frames
streaming
error
drift
In training the student continues from clean past frames. When streaming it continues from its own, and small errors add up.
Exposure bias returns once the student streams
[19] Huang et al. 2025, arXiv:2506.08009 · [50] Yin et al. 2025, arXiv:2412.07772
56
training
Off-policy context
On-policy context
Teacher forcing
ground truth
Gθ
≠
Diffusion forcing
noised ground truth
Gθ
≠
its own rollout
Gθ
=
inference
Gθ
Same Wan2.1-1.3B base, VBench total: Self Forcing 84.31, CausVid's recipe 81.20.
Self Forcing trains on its own rollouts
[19] Huang et al. 2025, arXiv:2506.08009
57
Causal student Gθ
rollout
it conditions on its own frames
+ noise
Real score
Wan2.1-14B, frozen
Fake score
trained on rollouts
DMD loss
on the whole clip
gradient through the rollout
On one H100, 17.0 FPS and a 0.69 s first frame. VBench 84.31.
CausVid oversaturates, Self Forcing does not
[19] Huang et al. 2025, arXiv:2506.08009 · CC BY-NC-SA 4.0 (inferred)
58
Wan2.1-1.3B
teacher
4 steps
4 steps
saturated,
smoothed
One prompt, four seconds
Self Forcing drifts after five seconds
[61] Liu et al. 2025, arXiv:2509.25161, Fig. 4 · CC BY 4.0, cropped
59
0 s
120 s
Rolling
Forcing
Self
Forcing
drift starts here
Imaging drift over 30 s: Self Forcing 1.66, Rolling Forcing 0.01
Video students lose variety too
60
82
83
84
0.08
0.12
VBench total
Diversity across 5 seeds
teacher
same score, 57% of the spread
What the big labs ship for video
[53] Zheng 2026 · [113] NVIDIA 2025 · [81] Zheng 2026 · [47] Lin 2025 · [64] Lin 2025 · [19] Huang 2025 · [17] ModelTC 2025
61
steps
family
NVIDIA
1 to 4
trajectory
distribution
Cosmos-Predict2.5
4
trajectory
distribution
2 to 4
trajectory
distribution
streams
ByteDance Seed
1
discriminator
1
discriminator
streams
others
4
distribution
streams
4
distribution
one step per latent frame
Distillation from 2015 to 2026
62
the old way
the problem
now
knowledge
distillation
2015
DDPM
UC Berkeley
2020
progressive
distillation
2022
guidance
distillation
Google, Stanford
consistency
models
OpenAI
2023
Stability AI
MIT, Adobe
MIT, Adobe
2024
OpenAI
Adobe, UT Austin
2025
NVIDIA, Tsinghua
Tsinghua, NVIDIA
2026
one step blurs
Part 7
What still breaks
What do the scores not show?
Problems nobody has solved yet
64
Long videos drift
Variety drops and is hard to measure
FID and GenEval disagree
SD3.5-Flash, DMD2
One-step video still needs a discriminator
Latency numbers skip the VAE
SDXS, APT
one DMD2, three LPIPS values
Where I would start
65
images
1
SDXL teacher
2
3
5 fake-score
updates
4
4 steps
5
check variety
about 60 h on 64 A100s
video
1
Wan teacher
2
ODE init
3
4
rolling cache
5
check drift
about 600 iterations on 64 H100s
Give the teacher the same wall-clock before you call it a win.
Using a distilled model takes a few lines
[1] Yin 2024 · model card: huggingface.co/tianweiy/DMD2 · image CC BY 4.0
66
pipe = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
torch_dtype=torch.float16, variant="fp16").to("cuda")
pipe.load_lora_weights(hf_hub_download(
"tianweiy/DMD2", "dmd2_sdxl_4step_lora_fp16.safetensors"))
pipe.fuse_lora(lora_scale=1.0)
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
image = pipe(prompt="a photo of a cat",
num_inference_steps=4, guidance_scale=0,
timesteps=[999, 749, 499, 249]).images[0]
LCM defaults differ from training
1
load teacher pipeline
2
swap in student weights
3
4 steps, guidance off
Which kind of distillation to pick
67
Family | Matches | Target from | Trained on | Weak spot |
a teacher ODE point | teacher | off-policy | few-step blur, teacher ceiling | |
Self-distillation CT, shortcut, MeanFlow | its own stop-gradient output | self | off-policy | from scratch, ImageNet only |
Distribution | teacher score minus fake score | teacher | on-policy | mode dropping, frozen guidance |
a discriminator's verdict | teacher | on-policy | collapse, lower diversity |
on-policy still has a teacher
References
68
[1] Yin 2024, arXiv:2405.14867
[2] Blau 2018, arXiv:1711.06077
[3] Robbins 1956, projecteuclid.org
[4] Efron 2011, doi.org
[5] Dieleman 2024, sander.ai
[6] Salimans 2022,�arXiv:2202.00512
[7] Hinton 2015, arXiv:1503.02531
[8] Kim 2016, arXiv:1606.07947
[9] Gu 2024, arXiv:2306.08543
[10] Agarwal 2024,�arXiv:2306.13649
[11] Lu 2025, thinkingmachines.ai
[12] Lightricks 2026, huggingface.co
[13] Black Forest Labs 2024,�huggingface.co
[14] Stability AI 2024,�huggingface.co
[15] Bandyopadhyay 2025,�arXiv:2509.21318
[16] Chen 2025, arXiv:2503.09641
[17] ModelTC 2025, github.com
[18] Huang 2025, github.com
[19] Huang 2025, arXiv:2506.08009
[20] Meng 2023, arXiv:2210.03142
[21] Dieleman 2022, sander.ai
[22] Bradley 2024, arXiv:2408.09000
[23] Karras 2024, arXiv:2406.02507
[24] Luo 2023, arXiv:2310.04378
[25] Luo 2023, arXiv:2311.05556
[26] Ren 2024, arXiv:2404.13686
[27] Song 2023, arXiv:2303.01469
[28] Song 2024, arXiv:2310.14189
[29] Kim 2024, arXiv:2310.02279
[30] Lu 2025, arXiv:2410.11081
[31] Liu 2022, arXiv:2209.03003
[32] Liu 2024, arXiv:2309.06380
[33] Frans 2025, arXiv:2410.12557
[34] Geng 2025, arXiv:2505.13447
[35] Boffi 2024, arXiv:2406.07507
[36] Sabour 2025, arXiv:2506.14603
[37] Zhou 2025, arXiv:2503.07565
[38] Wang 2023, arXiv:2305.16213
[39] Luo 2023, arXiv:2305.18455
[40] Yin 2024, arXiv:2311.18828
[41] Zhou 2024, arXiv:2404.04057
[42] Zhou 2025, arXiv:2406.01561
[43] Xie 2024, arXiv:2405.16852
[44] Sauer 2023, arXiv:2311.17042
[45] Sauer 2024, arXiv:2403.12015
[46] Lin 2024, arXiv:2402.13929
[47] Lin 2025, arXiv:2501.08316
[48] Xu 2023, arXiv:2311.09257
[49] Team Wan 2025,�arXiv:2503.20314
[50] Yin 2025, arXiv:2412.07772
[51] Li 2024, arXiv:2405.18750
[52] Li 2025, arXiv:2410.05677
[53] Zheng 2026, arXiv:2510.08431
[54] HaCohen 2025,�arXiv:2501.00103
[55] Kynkäänniemi 2019,�arXiv:1904.06991
[56] Naeem 2020, arXiv:2002.09797
[57] Ghosh 2023, arXiv:2310.11513
[58] Song 2024, arXiv:2403.16627
[59] Poole 2022, arXiv:2209.14988
[60] Yang 2025, arXiv:2509.22622
[61] Liu 2025, arXiv:2509.25161
[62] Cui 2025, arXiv:2510.02283
[63] Jiang 2025, arXiv:2511.13649
[64] Lin 2025, arXiv:2506.09350
[65] Gandikota 2025,�arXiv:2503.10637
[66] Huang 2024, arXiv:2311.17982
[67] Zhang 2025, arXiv:2510.20771
[68] Lee 2025, arXiv:2510.24474
[69] Geng 2025, arXiv:2512.02012
[70] Lu 2025, arXiv:2507.18569
[71] Ge 2025, arXiv:2506.00523
[72] Chang 2025, arXiv:2506.07977
[73] Shaul 2026, arXiv:2607.26004
[74] Chen 2025, arXiv:2510.14974
[75] Salimans 2024,�arXiv:2406.04103
[76] Zhou 2024, arXiv:2410.14919
[77] Xu 2025, arXiv:2502.15681
[78] Wang 2025, arXiv:2505.20755
[79] Cheng 2025, arXiv:2512.05150
[80] Wu 2026, arXiv:2602.03139
[81] Zheng 2026, arXiv:2606.25473
[82] Zhu 2026, arXiv:2602.02214
[83] Liu 2026, arXiv:2609.14725
[84] Wang 2024, arXiv:2405.18407
[85] Duan 2026, arXiv:2609.11265
[86] Fan 2025, arXiv:2510.27684
[107] Liu 2026, arXiv:2605.06376
[108] Black Forest Labs 2026,�huggingface.co
[113] NVIDIA 2025,�arXiv:2511.00062
Example images: [1], [44] CC BY 4.0; [19], [50] CC BY-NC-SA 4.0; [32] MIT; [53] Apache-2.0; web figures as cited. Cropped and combined.
Thanks
shreshthsaini.github.io/blogs/diffusion-distillation.html
Questions